检索结果-内蒙古大学图书馆

38th International Conference on VLSI Design, VLSID 2025

作者： Saha, Kritanta Banerjee, Pritha Sur-Kolay, Susmita Indian Statistical Institute Advanced Computing and Microelectronics Unit Kolkata India Sister Nivedita University Department of Computer Science and Engineering Kolkata India University of Calcutta Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798331522445

Given n points in the 2D plane which are the pins of a net, a Rectilinear Steiner Minimum Tree (RSMT) which consists only of vertical and horizontal line segments is the shortest network to interconnect the pins along with a few extra (Steiner) points. An RSMT for a net has a minimum total wirelength in Manhattan distance and acts as a backbone to many state-of-the-art global routers. However, finding an RSMT is NPcomplete. In this work, we propose a method for constructing an RSMT with an image-to-image translation using a conditional generative adversarial network (cGAN) based model. Images of RSMTs with optimal wirelength for randomly generated nets form our training dataset. Experimental results show that, after training, our model generates RSMTs with = 0.348% wirelength error on average compared with the optimal solution for nets with degrees up to 50. This is the first successful attempt to solve the RSMT construction problem as an image-to-image translation problem using a cGAN based model. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Guardians of Truth: Exploring Techniques for Veracity Identification in social media during an Infodemic 3

Guardians of Truth: Exploring Techniques for Veracity Identi...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Suthanthiradevi, P. Revathy, G. Sathish Kumar, P. Karthikeyan, B. Muthu, Lakshmi.V SRM institute of Science and Technology Data Science and Business Systems School of Computing India Vels Institute of science Technology and Advanced studies Department of Computer science and engineering India Rajalakshmi institute of technology Computer and Communication Engineering India SASTRA Deemed University School of Computing India St. Joseph's Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350372120

With the recent advent of technology, social networks are accessible 24/7 using mobile devices. During covid-19 pandemic the propagation of misinformation are mostly related to the disease, its cures and prevention. With Twitter as the medium this information was spreaded to millions of people who lack domain specific knowledge. This can lead to bloster fear and direct damage to the people. This research focuses on identifying the veracity of the Twitter posts behind pandemic situation. The authors have proposed a Transformer Model using Bat Algorithm for identifying the fake news. This model is trained and evaluated using infodemic metadata. Our experimental results shows by which proposed model accurately detected the fake news and achieved 96.5% of f1-score. © 2024 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Algorithmic Trading Based on News and Events Strategies 7th

Deep Learning-Based Algorithmic Trading Based on News and Ev...

引用

7th International Conference on Soft computing: Theories and Applications, SoCTA 2023

作者： Kayathri, V. Prabakaran, P. Department of Computer Applications School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Pallavaram Chennai600 117 India

ISBN: (纸本)9789819720309

Successful stock market investors should consider these trends. This article defines price effect, optimal execution, and placement through the lens of algorithmic trading and strategies based on news and events. By using feedbacks controlled to include consideration of a stop-loss order, algorithmic trading allows traders and investors at large to liquidate or construct big securities positions in a fully automated manner, thus generalising the existing stock trading results. Trading decisions made by the AI agent could affect the asset price. We see this as a marketplace where people are bartering and swapping goods. Creating a new market is the driving force behind our research into generative models. This news sentiment does a good job of describing stocks, and AI systems that read the news and quantify them react to factors that affect prices far more quickly than humans do. All three of the stock market's underpinnings—price, volume, and volatility—respond strongly to news events. Sentiment analysis is a method for gauging the overall tone of a news piece and classifying it as optimistic, pessimistic, or neutral. The simulation is conducted in python to test the effectiveness of the model in trading in an automated manner for stocks. The results show that the proposed sentimental analysis for stock trading achieves higher rate of accuracy and precision than the other methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

引用

science China(Information sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

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

Enhancing Wildlife Monitoring Through Infrared Imaging: A Deep Learning Approach for Improved Animal Region Segmentation and Species Identification

引用

Journal of Harbin institute of Technology(New series) 2024年

作者： V Janani C Shanthi Department of Computer Science， School of Computing Sciences， Vels Institute of Science Technology and Advanced Studies

Infrared imaging has proven to be a powerful tool in various fields， with particular significance in wildlife monitoring. In this paper， we present an extension of our previous research， focusing on advancing the segmentation of animal regions in enhanced infrared images and expanding the scope to include species identification. Our proposed methodology builds upon the success of the R-CNN (Region-based Convolutional Neural Network) object detection to improve the accuracy and robustness of animal region segmentation， while simultaneously extending our model’s capabilities to identify and classify the species within those regions. By fine-tuning the R-CNN model on a larger dataset that includes annotated infrared images and species labels， we enhance its capacity to not only accurately segment animal regions but also classify them into specific species categories. To assess the performance of our extended model， we employ a comprehensive set of evaluation metrics， including pixel-based metrics like Intersection over Union (IoU)， as well as species classification accuracy. Our results demonstrate significant improvements in both region segmentation accuracy and species identification compared to our previous work and existing methods. This research showcases the potential of deep learning techniques， combined with transfer learning， to advance wildlife monitoring applications using infrared imaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum Machine Learning Techniques based on Nurturing Agri-Ontology Framework in Agricultural science 3

Quantum Machine Learning Techniques based on Nurturing Agri-...

引用

3rd International Conference on Applied Artificial Intelligence and computing, ICAAIC 2024

作者： Deepa, R. Jayalakshmi, V. Thilakavathy, P. Bennet Prabhu, A. Surendran, R. Srm Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India Drbccc Hindu College Department of Computer Applications Chennai India Computer Science and Engineering Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Kone Elevator India Technology & Engineering Centre Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350375190

The absence of a consistent ontological framework often impedes efficient knowledge organization and sharing within the agricultural community, despite the quantity of data created in agricultural research. The lack of defined vocabulary and conceptual frameworks hinders data integration, agricultural research, and innovation by preventing interoperability between databases and systems. To address these issues, this research work proposes the Nurturing Agri-Ontology Framework (NAOF), which offers a systematic approach to creating and updating agricultural ontologies. Ontologies that faithfully portray agricultural ideas and connections can be more easily created with the help of NAOF, which combines ideas from knowledge management, agricultural science, and ontology engineering. NAOF aims to ensure that the ontologies produced reflect the wide range of viewpoints and terminology used in agricultural research by encouraging cooperation among stakeholders, ontology engineers, and domain specialists. In this study, the improvement of knowledge organization, sharing and integration in the agricultural area is shown with the application of NAOF. Using this research study, scientists can build ontologies that improve agricultural decision-making, data interoperability, and the discovery of new information. Using quantum machine learning techniques, a strong foundation of knowledge can be laid for several agricultural applications, such as precision agriculture, crop management, and the formulation of agricultural policies. Ontology coverage, interoperability, scalability, and usability are established evaluation parameters that are used to assess the efficacy of NAOF in this research work. The analysis shows that NAOF effectively solves the problems and creates a better agricultural knowledge ecosystem by thoroughly evaluating it using these standards. © 2024 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Improved Contextual Understanding and Emotion Detection in Large-Scale Text Data with Hybrid Deep Learning Models 5

Improved Contextual Understanding and Emotion Detection in L...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Thilakavathy, P. Manikandan, G. Deepa, R. Jayalakshmi, V. Surendran, R. Computer Science and Engineering Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India St. Joseph's College of Engineering Anna University Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM institute of science and technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Ramapuram Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

With the growth of large-scale text datasets from reviews, social media, and other online sources, sentiment analysis is essential for understanding public opinion. Traditional models struggle to understand complicated linguistic sentiments and interdependencies. This research could improve sentiment classification in customer feedback analysis, market sentiment predictions, and social media monitoring. Addressed issues include ambiguous language, sentence context flipping, and the need for robust models that can manage massive datasets. Contextual Detection Text Analysis Using Deep Learning (CDTA-DL) improves contextual knowledge and emotion identification in this research. RNNs and CNNs are used in the CDTA-DL approach to extract spatial and sequential information from text. CDTA-DL helps large-scale sentiment analysis detect sarcasm, implicit emotions, and many expressions. In a comprehensive simulation investigation employing open-access sentiment analysis datasets, CDTA-DL surpassed standard deep learning models in accuracy, recall, and F1 scores. The recommended strategy may increase emotion recognition and contextual understanding, making it ideal for large-scale sentiment analysis in various domains. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Sentiment Analysis with Adaptive Neural Networks for Emotion Classification 5

Deep Learning for Sentiment Analysis with Adaptive Neural Ne...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Jayalakshmi, V. Thilakavathy, P. Manikandan, G. Deepa, R. Surendran, R. SRM Institute of Science and Technology Department of Computer Science and Applications Tamilnadu Chennai India Computer Science and Engineering Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM institute of Science and Technology Department of Computing Technologies Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

In understanding human emotions, sentiment analysis has been invaluable in social media monitoring, consumer comment analysis, and psychological evaluations. Customer service, human-computer interface, and public mood comprehension depend on appropriate emotion categorisation. Despite its potential, sentiment analysis struggles with sarcasm, multimodal data integration, and emotion processing. Implementing real-time applications requires improving deep learning model computational complexity. Multimodal Optimised Emotion Analysis using Deep Learning (MOEA-DL) uses CNNs for image processing, RNNs for text., and LSTM networks for sequential audio data. This improves emotion recognition by combining modality strengths. Marketing sentiment, mental health monitoring, social media sentiment, and consumer feedback use MOEA-DL. Multimodal solutions are better than text-based ones for communicating emotion. Customer contacts, film reviews, and social media platforms are used to evaluate the proposed strategy. According to simulations, MOEA-DL categorises emotions more accurately and robustly than previous sentiment analysis methods. Its adaptive neural network lets the system learn and perform well in many cultural and language environments. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Enhanced Camouflage Detection Using advanced Image Processing Techniques for Real-Time Object Recognition and Pattern Differentiation 5

Enhanced Camouflage Detection Using Advanced Image Processin...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Manikandan, G. Deepa, R. Jayalakshmi, V. Thilakavathy, P. Surendran, R. St. Joseph's College of Engineering Anna University Department of Artificial Intelligence and Machine Learning Chennai India School of Computing SRM Institute of Science and Technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Chennai India Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Computer Science and Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

The identification of objects that blend in with their surroundings has long been a concern in fields including defence, wildlife monitoring, and surveillance due to the difficulty of detecting such objects. This finding is significant because it could greatly enhance our capacity to detect camouflaged objects, transforming the field of real-time object detection. Existing image processing methods often fail miserably when adequately capturing this aspect. This dissertation's primary focus is identifying devices with complicated patterns, legacy interference, and inadequate contrast;nonetheless, in disguised scenarios, all of these features cause identification to be unsuccessful. This research often suggests a new approach called the Linear Edge Detecting Scheme for Camouflaged Object Detection (LEDS-COD) in these difficult cases. The LEDS-COD system can enhance item visibility in low-comparison settings by highlighting critical edges and descriptions. Pattern differentiation methodologies and modern facility-side recognition techniques are combined to accomplish this goal. The approach successfully differentiated items because it zeroed in on texture and comparative details that would otherwise go unnoticed by humans or advanced algorithms. LEDS-COD is useful in many areas, including the Navy, autonomous surveillance systems, and animal protection, where the real-time identification of hidden devices is essential. Results from a simulation study using various datasets, including concealed objects, show that LEDS-COD surpasses conventional detection methods in recognition accuracy, processing speed, and perseverance. The recommended technique exceeded the requirements for obtaining improved object detection estimates for challenging conditions like those with complex backdrops and changing illumination. According to this study, LEDS-COD can be devastating in improving real-time camouflage detection. © 2024 IEEE.

关键词： Accuracy Image processing Surveillance Image edge detection Wildlife Lighting Object detection Real-time systems Object recognition Protection

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：