检索结果-内蒙古大学图书馆

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing, AIAHPC 2023

作者： Liang, Fengqi Wang, Licai Yu, Jintao North China Institute of Computing Technology Big Data R&D Center China

ISBN: (数字)9781510666580

ISBN: (纸本)9781510666573

This paper proposes a ship detection method based on contour extraction networks and minimum bounding box generation algorithms. The proposed method utilizes contour extraction networks to extract the contour of the ship target and generate a set of key points. Then, the minimum bounding box generation algorithm is used to transform these key points into the rotational detection box of the target, which can more accurately describe the shape and orientation of ships, thus improving the accuracy and reliability of detection. The experimental results show that the proposed method can effectively detect ships of various orientations and postures, and has better performance than traditional rectangular box detection methods. The paper compares rotated bounding box detection methods based on traditional machine learning and deep learning, and concludes that rotated bounding box detection methods based on deep learning can better solve the problem of ship detection in complex situations, but require a large amount of data for training and may require a higher computational cost. Finally, the paper introduces the Minimum Bounding rectangle Algorithm used in the instance segmentation process. © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

robust and efficient keyword spotting using a bidirectional attention LSTM

引用

International Journal of Speech technology 2023年第4期26卷 919-931页

作者： Swain, Om Prakash Hemanth, H. Saran, Puneet Kothandaraman, Mohanaprasad ravi, Logesh Sailor, Hardik rajesh, K.S. Vellore Institute of Technology Chennai600127 India Centre for Advanced Data Science Vellore Institute of Technology Chennai India Samsung R&D Institute Bangalore560037 India

Speech recognition and voice assistants have become integral in various advanced electronic devices and human-computer interfaces ranging from smartphones to self-driving cars. Personal assistants like Google Assistant and Amazon Alexa are state-of-the-art examples of personal voice assistants triggered by simple wake words. Much research has been conducted on improving wake word detection and keyword spotting techniques. Along those lines, this research aimed to build an enhanced keyword-spotting model with high accuracy and reduced training time. The proposed model involves a Convolutional Neural Network and a bidirectional attention LSTM network. Another critical area of focus in this paper is audio pre-processing, where the Spectral gating technique has been introduced for denoising the data. The aforementioned CrNN model exploiting the abilities of CNN and LSTM was trained on this denoised data. The model has trained on 35 keywords from the Google Speech Commands dataset and can identify each. The model training was performed using Google Colab. The model proposed in this paper achieved a training accuracy of 93.44% and a test accuracy of 92.94%. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Wakes

来源：评论

学校读者我要写书评

暂无评论

Multi Party Secure Android Cash register

Multi Party Secure Android Cash Register

引用

2024 International Conference on Artificial Intelligence, Computer, data Sciences, and Applications, ACdSA 2024

作者： Cimen, Keziban Gokturk, Mehmet E Data Elektronik A.Ş R&d Center İstanbul Turkey Institute of Information Technology Gtu Gebze Turkey

ISBN: (纸本)9798350394528

As businesses prioritize integration with applications like ErP and inventory tracking, the Android Cash register POS device emerges as a transformative solution, aligning with modern POS trends. developed with a focus on usercentered design principles, the Android Cash register stands out as the first of its kind in the market. It ensures a decade-long usability, encompassing both hardware and software aspects. This study focuses on multipary software enabled Cash register POS device's compatibility with digital transformations its collaborative development, and its potential for increased market share internationally. Key features of such a POS device include remote control capabilities, compliance with high-level financial regulations, and the unique combination of being a Payment recording device (ECr) with EFTPOS capabilities. The study introduces a Multi-Stakeholder Android Cash register connected to a Secure remote Software distribution Network, offering a distinctive product globally. The hardware design incorporates security measures like MESH and Electronic Seal to safeguard against physical impact and tampering. Security factors, including signing mechanisms like Sign2, are discussed, highlighting the enhanced protection against tampering attacks and the utilization of robust hash algorithms. The study also focuses on Android's role in the payment sector, addressing security vulnerabilities related to internet access and NFC. In short, importance of a multi-party store model is emphasized, allowing only approved applications to run on the secure Android POS device. The proposed Android Cash register represents a significant leap, offering a secure, integrated, and technologically advanced solution to meet evolving business needs in the digital era, all within a concise framework. © 2024 IEEE.

关键词： Cash registers

来源：评论

学校读者我要写书评

暂无评论

Mitigation of Subsynchronous Control Interaction in dFIG-Based Wind Farm Using SdC-LAdrC

Mitigation of Subsynchronous Control Interaction in DFIG-Bas...

引用

2024 CPSS and IEEE International Symposium on Energy Storage and Conversion, CPSS and ISESC 2024

作者： Chen, Binbin Zhang, damin Cao, Jiongqiong Zhong, Yichuan Huang, Jinping Zhang, Yuanzhong College of Electrical Engineering and Automation Xiamen University of Technology Xiamen China Kehua Data Co Ltd Kehua Data R&D Center Xiamen China

ISBN: (纸本)9798350380514

The interaction between wind farms based on doubly-fed induction generators (dFIG) and series capacitors in transmission lines can result in sub-synchronous control interaction (SSCI). due to the influence of system conditions on the oscillation frequency of SSCI, traditional supplementary sub-synchronous damping control (SSdC) methods, which rely on phase compensation and filtering parameters, become inadequate under varying conditions. To address this issue, this paper proposes a novel supplementary damping-based linear active disturbance rejection control (SdC-LAdrC) approach to mitigate SSCI in various scenarios. First, a supplementary damping controller (SdC) is designed to enhance positive damping on the rotor side. Next, the combination of LAdrC control and SdC replaces rotor-side converter (rSC) inner loop control. The SdC-LAdrC controller leverages the linear extended state observer (LESO) within the LAdrC framework to estimate subsynchronous disturbances and provide real-time feedback compensation. This approach effectively suppresses SSCI at full compensation levels, outperforming traditional SSdC methods. Finally, the effectiveness of proposed control method is verified through MATLAB/ Simulink simulation tools. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Traffic Prediction in Urban Area using Convolutional Temporal Network System 6

Spatio-Temporal Traffic Prediction in Urban Area using Convo...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Priya, K. Omkar, K. Naresh, r. Venkatesh, K. Dept. of Artificial Intelligence and Data Science Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331522667

Traffic prediction in urban areas is essential for smart city applications, enabling efficient transportation management, reduced congestion, and improved quality of life. Spatiotemporal traffic prediction is particularly challenging due to complex spatial and temporal dependencies in traffic data. This study introduces a Convolutional-Temporal Neural Net- work System (CTNS) model that combines Convolutional Neural Networks (CNNs) and recurrent Neural Networks (rNNs) to capture spatial and temporal features simultaneously for more accurate traffic forecasting. CNNs are employed to learn spatial correlations between different locations in the urban area, while rNNs, specifically Long Short-Term Memory (LSTM) networks, capture the sequential dependencies in temporal traffic patterns. Using real-world traffic data, the hybrid CTNS model demonstrates superior performance in accurately predicting traffic flow compared to traditional models. This approach highlights the potential of deep learning architectures for enhancing the accuracy of traffic predictions, which is critical for urban planning and intelligent transportation systems. Extensive experiments on real-world urban traffic datasets validate the model’s ability to achieve high accuracy, scalability, and robustness in handling complex spatio-temporal interactions. © 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

Exploring deep Neural Networks for Accurate diabetic retinopathy Prediction

Exploring Deep Neural Networks for Accurate Diabetic Retinop...

引用

2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024

作者： Kujani, T. Arivubrakan, P. raju, K. Sankar, P. Mani reddy, B. Surekha Bhavana, E. Computer Science And Engineering Vel Tech Rangarajan Dr. Sagunthala R&d Institute Of Science And Technology Chennai India Artificial Intelligence And Machine Learning Vel Tech Rangarajan Dr. Sagunthala R&d Institute Of Science And Technology Chennai India Artificial Intelligence And Data Science Vel Tech Rangarajan Dr. Sagunthala R&d Institute Of Science And Technology Chennai India

ISBN: (纸本)9798350352689

diabetic retinopathy (dr) emerges as a serious complication associated with diabetes mellitus, causing damage to retinal blood vessels, and resulting in vision loss. The critical need for early detection and effective management to curb the progression towards vision impairment and potential blindness underscores the significance of this issue. To address these challenges, have propose a novel deep learning system utilizing a densely connected Convolutional Network (denseNet-201) for the efficient detection of dr. This model is specifically trained to classify fundus images into six distinct categories: no dr, mild, moderate, and severe, proliferative dr, and hard exudates. The datasets utilized in this study include the publicly available diabetic retinopathy detection 2015 and Aptos 2019 blindness detection datasets from Kaggle. The proposed system comprises multiple stages, including data Collection, Preprocessing, Augmentation, and Modeling. during the preprocessing phase, normalization techniques are to eliminate biases or distortions present in the fundus images. Furthermore, the augmentation of data is employed to enhance the diversity and quantity of the training dataset. In the modeling stage, have designed and implemented the deep learning model, with the robust and high-performing denseNet-201 architecture selected as the model's backbone. The model exhibits a significant accuracy of 87.7% in its classification task. Additionally, have introduced a deep Neural Network (dNN) model, achieving an impressive accuracy rate of 95.8%. These results underscore the effectiveness of our proposed system in accurately and efficiently detecting dr. The primary objective of this research is to develop a reliable and automated system for diabetic retinopathy detection, with the overarching goal of improving the quality of life for individuals affected by diabetes. © 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

ANALYSIS OF GLOBAL r&d TrENdS IN NATUrAL COSMETICS BASEd ON PATENT BIBLIOMETrICS 21

ANALYSIS OF GLOBAL R&D TRENDS IN NATURAL COSMETICS BASED ON ...

引用

21st International Conference on Applied Computing 2024, AC 2024 and 23rd International Conference on WWW/Internet 2024, ICWI 2024

作者： Sohn, Eunsoo Seo, Jinny Lee, Chang-Hoan Center for Global R&D Data Analysis Korea Institute of Science and Technology Information 66 Hoegi-ro Dongdaemun-gu Seoul Korea Republic of

ISBN: (纸本)9789898704627

Natural cosmetics including nature-derived cosmetic materials, are growing significantly in line with global S&T trends such as eco-friendliness, sustainability, and technology convergence. In particular, due to concerns about air pollution and the rapid increase in skin disease patients such as allergies and atopy, the demand for natural cosmetics known to be safe and cause little skin irritation is increasing. In this study, through bibliometric analysis of 233,281 patent literature data we analyzed the global technology trends in natural cosmetics and the r&d level and competitiveness of Korean natural cosmetics leading the Korean Wave (Hallyu) and K-beauty. Network analysis, text mining, and machine learning using large language model were used to extract, cleaning, and analyze keyword from big text documents. These bibliometric big data analysis can help identifying development trends in natural cosmetics and provide important insights for establishing patent or r&d strategies. © 2024 Proceedings of the International Conferences on Applied Computing and WWW/Internet 2024. All rights reserved.

关键词： Cosmetics

来源：评论

学校读者我要写书评

暂无评论

Improving Sign Language recognition for deaf and Hard of Hearing Individuals using the VGG16 Model 3

Improving Sign Language Recognition for Deaf and Hard of Hea...

引用

3rd International Conference on Automation, Computing and renewable Systems, ICACrS 2024

作者： Benjamin, Minu Inba Shanthini Watson Patan, Yaseen Kumar, Ansilin S.M. reddy, Pocharam Nithyanandh Ahamad, Syed Faheez Puneeth, Muvvala Sai Department of Computer Science & Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Artificial Intelligence and Data Science Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331532420

Persons who are deaf and who cannot speak face a variety of challenges, which emphasises the need for greater research to offer appropriate assistance. Interaction and communication with others are a big challenge. Since sign language is the major means of communication for these people, there is a significant knowledge gap among hearing individuals when it comes to understand and interpret sign language. As a result, there has been a notable expansion in the field of sign language study to close this gap. This work highlights the importance of sign language detection and offers a thorough analysis of relevant studies carried out in this domain using deep learning technique. It approaches the issue from multiple perspective, including translation, sign language recognition, and access to relevant datasets. Understanding these facets is intended to create a meaningful impact on sign language literature and its practical implementation. VGG16 deep learning model for sign language recognition offers the best solution for solving communication challenges faced by deaf and muted individuals. The results show that the VGG16 based technique achieves accuracy of around 95.8%. The VGG16 model uses a Convolutional Neural Network (CNN) architecture, which applies many layers of convolutional filters to identify patterns and attributes in the input images. recognizing sign language using VGG16. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Image Caption Generation using CNN and Audio Conversion 2

Image Caption Generation using CNN and Audio Conversion

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Priya, K. Babu, r.Vijay reddy, M.Muralidhar Mohan reddy, T.H. Maanesh, M. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Artificial Intelligence & Data Science Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Arizona state university Department of Data Science Tempe United States

ISBN: (纸本)9798350368413

This research focuses on developing a system that can generate descriptive captions for images and convert them into audio output. The system employs a Convolutional Neural Network (CNN) to extract visual features from images, which are then fed into a Gated recurrent Unit (GrU) to generate textual descriptions. The generated captions are subsequently converted into audio using text-to-speech techniques. By training the model on a large dataset of image-caption pairs, the system learns to associate visual information with textual descriptions, enabling accurate and coherent caption generation. This research contributes to the advancement of image understanding and generation, with potential applications in various fields such as image search, accessibility, and content creation. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A disk Failure Prediction Algorithm Based on Fusion Model 23

A Disk Failure Prediction Algorithm Based on Fusion Model

引用

15th International Conference on Machine Learning and Computing, ICMLC 2023

作者： Zhao, Liqiang Qi, Kaiyuan Su, Zhiyuan Pang, Liye Zhang, Lianfa Wu, dong Cloud Computing R&D Department of Jinan Inspur Data Technology State Key Laboratory of High-end Server & Storage Technology China

ISBN: (纸本)9781450398411

disk failure prediction is of great significance for ensuring the business continuity and data reliability of cloud data centers. Algorithm performance will directly affect operation and maintenance costs and user experience. Nowadays, many disk manufacturers use the threshold of S.M.A.r.T. data to check disk fault detection or make prediction, but the detection accuracy of this method is low. This paper proposes a disk fault prediction method based on deep learning, using deep residual network to extract high-dimensional hidden features;and using deep neural network combined with integrated tree model tool XGBoost to perform Failure prediction. Moreover, we use AutoML strategy based on improved GA to get the best model structure. Experiments based on Backblaze data show that this method has better prediction performance. Compared with pure XGboost methods, it can better reduce the false alarm rate about 50% and improve the accuracy rate, while maintaining a strong generalization ability. © 2023 ACM.

关键词： Fault 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：