检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Guo, Pinxue Li, Wanyun Huang, Hao Hong, Lingyi Zhou, Xinyu Chen, Zhaoyu Li, Jinglun Jiang, Kaixun Zhang, Wei Zhang, Wenqiang Shanghai Engineering Research Center of Ai & Robotics Academy for Engineering & Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Engineering Research Center of Ai & Robotics Ministry of Education Academy for Engineering & Technology China

ISBN: (纸本)9798400706868

Multi-modal Video Object Segmentation (VOS), including RGB-Thermal, RGB-Depth, and RGB-Event, has garnered attention due to its capability to address challenging scenarios where traditional VOS methods struggle, such as extreme illumination, rapid motion, and background distraction. Existing approaches often involve designing specific additional branches and performing full-parameter fine-tuning for fusion in each task. However, this paradigm not only duplicates research efforts and hardware costs but also risks model collapse with the limited multi-modal annotated data. In this paper, we propose a universal framework named X-Prompt for all multi-modal video object segmentation tasks, designated as RGB+X. The X-Prompt framework first pre-trains a video object segmentation foundation model using RGB data, and then utilize the additional modality of the prompt to adapt it to downstream multi-modal tasks with limited data. Within the X-Prompt framework, we introduce the Multi-modal Visual Prompter (MVP), which allows prompting foundation model with the various modalities to segment objects precisely. We further propose the Multi-modal Adaptation Experts (MAEs) to adapt the foundation model with pluggable modality-specific knowledge without compromising the generalization capacity. To evaluate the effectiveness of the X-Prompt framework, we conduct extensive experiments on 3 tasks across 4 benchmarks. The proposed universal X-Prompt framework consistently outperforms the full fine-tuning paradigm and achieves state-of-the-art performance. Code: https://***/PinxueGuo/*** © 2024 ACM.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Models for Plant Disease Detection using Transfer Learning Technique 10

Hybrid Models for Plant Disease Detection using Transfer Lea...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Sharma, Pavan Yadav, Rakesh Kumar Rawat, Sur Singh Iftm University Department of Computer Science and Engineering Moradabad244102 India Maharishi University of Information Technology Department of Computer Science and Engineering Lucknow226013 India Jss Academy of Technical Education Department of Computer Science and Engineering Noida201301 India

ISBN: (纸本)9789380544472

Plant diseases can sometimes be so bad that there is no grain harvest at all. Consequently, there is a great need for automatic plant disease identification and diagnosis in the realm of agricultural informatics. Many approaches have been put forth to solve this problem, but deep learning is quickly winning popularity due to its outstanding results. In this study, we assess the transfer learning capabilities of deep convolutional neural networks for the diagnosis of plant leaf diseases. We also consider how well the trained model will perform when applied to the specific task identified by our own data. One of the deep learning methods, the convolutional neural network algorithm (CNN), has been successfully applied to solve computer vision issues such as image classification, object segmentation, picture analysis, etc. In our study, we apply the Densenet201, Xception, InceptionResnetv2, NasNetMobile and VGG-16, hybrid with Support vector machine (SVM) along with a transfer learning approach to recognize diseases in images of different leaves. Instead of starting the training from scratch and arbitrarily initializing the weights, we use the pre-trained networks on the large labelled dataset, ImageNet, to build the weights. The proposed method's validity is supported by experimental findings, and it effectively detects plant diseases. The suggested method significantly outperforms other cutting-edge approaches in terms of performance like (F-scores of 0.93) for VGGG16+SVM, (F-score: 0.97) for DenseNet201+SVM, (F-score: 0.87) for Xception+SVM, (F-score: 0.97) for InceptionResnetv2+SVM, and (F-score: 0.93) NasNetMobile+SVM hybrid model on the dataset of plant images. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of MANET Routing Protocols on Cluster Head selection: with fuzzy logic approach and without fuzzy logic approach 9

A Comparative Analysis of MANET Routing Protocols on Cluster...

引用

9th International Conference on Smart Computing and Communications, ICSCC 2023

作者： Jose, Mitha Rachel Vigila, S. Maria Celestin Noorul Islam Centre for Higher Education Department of Computer Science and Engineering Tamilnadu Kumaracoil India Noorul Islam Centre for Higher Education Department of Information Technology Tamilnadu Kumaracoil India

ISBN: (纸本)9798350314090

A Mobile Ad hoc Network (MANET) is a self-organizing and dynamic network of mobile nodes that does not have a fixed infrastructure. Routing protocols play a crucial role in ensuring efficient communication between nodes in MANET. The selection of Cluster Head (CH) is a critical task that affects network performance. This paper presents a comparative analysis of MANET routing protocols on CH selection using two approaches: with fuzzy logic and without fuzzy logic. The fuzzy logic approach utilizes a mathematical model to handle imprecise or vague information to determine the best CH. The without-fuzzy logic approach uses traditional mathematical models to select the CH based on different metrics. The comparative analysis reveals the effectiveness of fuzzy logic in selecting CH in MANET routing protocols and the strengths and weaknesses of each approach. This study can provide valuable insights into the performance of different MANET routing protocols and their impact on CH selection, which can help improve the overall efficiency of MANETs. © 2023 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

MahitiBandhu: A Solar-Powered information Kiosk System for Rural Community Empowerment

MahitiBandhu: A Solar-Powered Information Kiosk System for R...

引用

2024 IEEE International Conference on information technology, Electronics and Intelligent Communication Systems, ICITEICS 2024

作者： Arakeri, Megha P. Lakshmana Jain, Ayush Hemachandra, G. Mohan Gowda, V. Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Computer Science and Engineering Manipal India Seamovations Labs Pvt. Ltd Bangalore India Ramaiah Institute of Technology Department of Information Science and Engineering Bangalore India Ramaiah Institute of Technology Department of Electrical and Electronics Engineering Bangalore India Gitam School of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350382693

A major portion of Karnataka's population lives in rural areas. Most of the rural people are illiterate and poor due to lack of proper services and infrastructure. There are various rural development schemes run by the government of Karnataka/India for the benefit of villagers. However, most people in the villages of Karnataka are unaware of these schemes due to lack of education, poverty, inaccessibility, and lack of technological knowledge. Hence, the government is trying to render services and information to the public using ICT tools. While there are few examples of achievements of ICT in rural development, there are many failures due to lack of connectivity, bandwidth, language problems, and power supply. Also, Gram Panchayat of the village does not have proper facilities to give widespread publicity about government services and many people do not have smartphones to access information online. Thus, this paper focuses on the development of a solar-powered interactive touch-screen based kiosk system for the rural region. This single system can provide information about all rural schemes for education, agriculture, healthcare, and employment. It also gives information on other services like banking, vaccination drives, and fertilizers for farmers. This is an end-to-end user application with a text-free user interface and interacts based on audio, video, and image display irrespective of the user's literacy level. © 2024 IEEE.

关键词： Touch screens

来源：评论

学校读者我要写书评

暂无评论

Robust Reversible Audio Watermarking Scheme for Telemedicine and Privacy Protection

引用

computers, Materials & Continua 2022年第5期71卷 3035-3050页

作者： Xiaorui Zhang Xun Sun Xingming Sun Wei Sun Sunil Kumar Jha Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science&TechnologyNanjing210044China IT Fundamentals and Education Technologies Applications University of Information Technology and Management in RzeszowRzeszow Voivodeship100031Poland

The leakage of medical audio data in telemedicine seriously violates the privacy of *** order to avoid the leakage of patient information in telemedicine,a two-stage reversible robust audio watermarking algorithm is proposed to protect medical audio *** scheme decomposes the medical audio into two independent embedding domains,embeds the robust watermark and the reversible watermark into the two domains *** order to ensure the audio quality,the Hurst exponent is used to find a suitable position for watermark *** to the independence of the two embedding domains,the embedding of the second-stage reversible watermark will not affect the first-stage watermark,so the robustness of the first-stage watermark can be well *** the second stage,the correlation between the sampling points in the medical audio is used to modify the hidden bits of the histogram to reduce the modification of the medical audio and reduce the distortion caused by reversible *** experiments show that this scheme has strong robustness against signal processing operations such as MP3 compression of 48 db,additive white Gaussian noise(AWGN)of 20 db,low-pass filtering,resampling,re-quantization and other attacks,and has good imperceptibility.

关键词： Telemedicine privacy protection audio watermarking robust reversible watermarking two-stage embedding

来源：评论

学校读者我要写书评

暂无评论

Optimizing Polynomial and Regularization Techniques for Enhanced Housing Price Prediction Accuracy

引用

SN computer Science 2025年第2期6卷 1-13页

作者： Preethi Murthy, D.H.R. Hiremani, Vani Devadas, Raghavendra M. Sapna, R. Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of CSE R L Jalappa Institute of Technology Visvesvaraya Technological University Karnataka Doddaballapur India Department of Computer Science and Engineering Symbiosis Institute of Technology International (Deemed University) Pune India

This study investigates the effectiveness of various regression models for predicting housing prices using the California Housing dataset. The models evaluated include Linear Regression, Ridge Regression, Best Polynomial Ridge Regression, Lasso Regression, Elastic Net Regression, and Support Vector Regression (SVR) with an RBF kernel. The analysis reveals that SVR with an RBF kernel exhibits the poorest performance, characterized by the highest Mean Squared Error (MSE) and the lowest R² score, indicating limited effectiveness for this dataset. Conversely, Linear Regression, Ridge Regression, and Best Polynomial Ridge Regression demonstrate significantly lower MSE values and nearly identical R² scores, each explaining approximately 60% of the variance in housing prices. Among these, Best Polynomial Ridge Regression marginally outperforms Linear and Ridge Regression, suggesting that including polynomial features enhances model performance. Although Lasso Regression shows slightly higher MSE than the leading models, it still performs better than Elastic Net and SVR. Overall, the study identifies linear regression, ridge regression, and best polynomial ridge regression as the most effective models for this dataset, with SVR and an RBF kernel being the least effective. © The Author(s) 2024.

关键词： Elastic net regression Lasso regression Linear regression Polynomial Ridge regression Regression techniques SVR with RBF regression

来源：评论

学校读者我要写书评

暂无评论

Answer Type Prediction: Unveiling the Power of Deep Learning Models 2

Answer Type Prediction: Unveiling the Power of Deep Learning...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Swathi, B.P. Geetha, M. Shenoy, Manjula Suhas, M.V. Manipal Institute of Technology Manipal Academy of Higher Education Department of Information & Communication Technology Manipal India Manipal Institute of Technology Manipal Academy of Higher Education Department of Computer Science and Engineering Manipal India Manipal Institute of Technology Manipal Academy of Higher Education Department of Electronics and Communication Engineering Manipal India

ISBN: (纸本)9798350308846

Answer type prediction plays a crucial role in natural language question answering systems, enabling the generation of relevant SPARQL queries, a query language for retrieving data from RDF databases. This research paper focuses on answer type prediction for SPARQL query generation. Answer type prediction involves identifying the expected type of the answer to a given question, such as a person's name, a location, or a numerical value. By accurately predicting the answer type, the subsequent SPARQL query generation process can be tailored to retrieve the desired information from a knowledge base. The proposed work evaluates the performance of four deep learning models, which include GRU (Gated Recurrent Unit), Bi-GRU, LSTM (Long Short-Term Memory), and Bi-LSTM. The study's conclusion highlights GRU as the top-performing model for predicting the answer type based on the analysis of input natural language queries. The performance of the answer type prediction model is evaluated on a publicly available dataset, demonstrating its effectiveness in achieving an accuracy of 81% using GRU. The results obtained from the study emphasize the importance of accurate answer type prediction and provide promising outcomes. © 2023 IEEE.

关键词： Answer type prediction Bi-GRU Bi-LSTM GRU LSTM Natural Language Processing Natural Language Query Question Answering Systems SPARQL

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Approach to Intelligent computer-Assisted Localization of Liver Tumor on Computed Tomography Images

引用

SN computer Science 2024年第7期5卷 809页

作者： Arakeri, Megha Lakshmana Reddy, Raghavendra Ravishankar, H. Deepa, K.R. Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal India Seamovations Labs Pvt Ltd Karnataka Bengaluru India School of Computer Science and Engineering REVA University Karnataka Bengaluru India School of Computer Science and Information Technology REVA University Karnataka Bengaluru India School of Electrical and Electronics Engineering REVA University Karnataka Bengaluru India

Computed Tomography (CT) Imaging is frequently used to find liver cancer. CT imaging of the liver generates cross-sectional images of the abdominal region. The task of segmenting a liver tumor on CT images is tedious due to the anatomic complexity of the liver. Therefore, liver tumor detection has been performed manually or semi-automatically which is an exhaustive process. Further, a tumor may be present on only some slices of the CT scan and hence there is a need to automatically identify images that contain tumors from acquired CT images and then locate a region of the tumor on those images for further diagnosis. Automatic detection helps the radiologist to obtain fast, accurate, and effective results. Accordingly, in this paper, an enhanced approach is proposed based on deep learning, efficient fuzzy c-means (EFCM) clustering, and a region-based algorithm for the detection of a liver tumor. A deep learning model built on a convolutional neural network is used to identify whether the CT image contains a tumor. If it contains the tumor, then the proposed EFCM and region-based algorithms are applied to locate the tumor on the CT image. The EFCM algorithm is combined with a region-based technique to automatically determine the initial pixel and threshold values required to segment the liver tumor. The proposed method is applied to several CT abdominal images. The results of the tumor segmentation are validated by comparing them with the tumor regions detected by radiologists. The estimated results of the experiment show that the proposed technique successfully detects the liver tumor on the CT image with less than 2% relative error. © The Author(s) 2024.

关键词： Computed tomography computer-aided detection Healthcare Liver tumor Medical image Segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of AI-Driven Natural Language Processing in Computational Analysis 15

Exploring the Impact of AI-Driven Natural Language Processin...

引用

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

作者： Singh, K. Ranjith Rajarajeswari, S. Kadam, Rutuja S. Kumar, Ravindra Agrawal, Trapty Raghavendra, R. Karpagam Academy of Higher Education Department of Computer Science Coimbatore641021 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Pune India Vivekananda Global University Department of Civil Engineering Jaipur India Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Department of Computer Science and Information Technology Karnataka Bangalore India

ISBN: (纸本)9798350370249

This paper explores the blessings of applying artificial intelligence and herbal language processing (NLP) strategies to massive-scale computation analysis. Natural language processing is fundamental to considering complex analytics tasks with relative ease using currently available technology. This paper mainly specializes in using NLP in the vicinity of sentiment evaluation. Sentiment evaluation uses numerous algorithms to determine sentiment from text, and it may be used to benefit insights from vast volumes of statistics. An exploration is performed to demonstrate the benefits of utilizing AI-driven NLP while appearing complicated sentiment analysis. The studies offer an overview of the techniques and equipment involved, as well as the demanding situations that should be confronted. Additionally, modern-day and potential programs are mentioned, together with their implications for company and purchaser decision-making. The paper concludes by providing several potential applications for AI-pushed NLP in the analytic space. Through the use of AI-pushed NLP, groups, and agencies can now gather and analyze records to benefit precious insights more effectively than ever before. © 2024 IEEE.

关键词： Potential Precious Programs Purchaser Records

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Detection Method Based on Improved YOLOv5s for Densely Occluded Scenarios 3

Pedestrian Detection Method Based on Improved YOLOv5s for De...

引用

3rd International Conference on Big Data, information and computer Network, BDICN 2024

作者： Pan, Rongting Qin, Guofeng Zhu, Yongjian Mi, Peiwen Li, Ming College of Electronic and Information Engineering Guangxi Normal University Guilin541004 China Teachers College for Vocational and Technical Education Guangxi Normal University Guilin541004 China School of Computer Science and Information Engineering Shanghai Institute of Technology Shanghai201418 China

ISBN: (纸本)9798350363821

In response to the issues of low accuracy and high false negatives in real-Time detection of densely occluded pedestrians, a pedestrian detection method based on improved YOLOv5s is proposed. This method involves replacing the Centralized-Comprehensive Convolution Block (C3) module in the backbone network with the DenseBlock module to enhance the model's feature extraction capabilities for small targets. The Efficient Intersection over Union (EIoU) loss function was used instead of the Complete Intersection over Union (CIoU) loss function to improve the model's ability to accurately locate densely occluded targets. Based on the feature pyramid structure, the Adaptive Spatial Feature Fusion (ASFF) module was introduced, enhancing the network's feature extraction capability. The introduction of the multi-head self-Attention (MHSA) mechanism has enhanced the model's adaptability. The experimental results indicate that the improved YOLOv5s algorithm achieves mAP0.5 and mAP0.5:0.95 of 78.6% and 48.7%, respectively, on the CrowdHuman dataset. This represents an improvement of 2.0% and 2.2% compared to the initial YOLOv5s. The detection time is 11.4ms, showing good robustness for detecting targets of different sizes and meeting real-Time requirements. © 2024 IEEE.

关键词： Feature extraction

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：