检索结果-内蒙古大学图书馆

43rd Chinese Control Conference, CCC 2024

作者： Li, Xingzhi Wang, Zhiwei Lang, Qi Liu, Xiaodong School of Control Science and Engineering Dalian University of Technology Dalian116024 China School of Computer Science and Information Technology Northeast Normal University Changchun130117 China

ISBN: (纸本)9789887581581

The internet's rapid expansion has generated abundant text data, posing a formidable challenge in extracting key information, where document clustering demonstrates its powerful role. Previously, many people commonly used a single clustering method, which may not be suitable for certain datasets. Additionally, documents are often represented as high-dimensional vectors, leading to the curse of dimensionality and sparsity issues, and clustering algorithms' effectiveness in high-dimensional spaces is limited. Therefore, this paper proposes a document ensemble clustering method based on dimensionality reduction, which can overcome the limitations caused by using a single clustering method, making it more suitable for the majority of text data. Initially, dimensionality reduction techniques are applied to preprocess document embeddings generated. Subsequently, these embedding vectors are fed into an ensemble clustering module, where distances between samples are computed using multiple clustering methods. By adjusting weights, the distance matrices are subjected to weighted summation to obtain an appropriate distance matrix. Finally, the K-means method is applied to cluster division, yielding the most suitable clusters for extracting the most relevant keywords. The proposed method was evaluated empirically, achieving excellent results on the 20Newsgroups and Reuters-21578 datasets. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Multi-Concept Learning for Scene Graph Generation

引用

IEEE Transactions on Image Processing 2025年 34卷 3366-3376页

作者： Lyu, Xinyu Gao, Lianli Xie, Junlin Zeng, Pengpeng Tian, Yulu Shao, Jie Shen, Heng Tao Southwestern University of Finance and Economics School of Computing and Artificial Intelligence Chengdu611731 China University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518000 China Ant Group Hangzhou China UESTC School of Computer Science and Engineering Chengdu China Shenzhen Institute for Advanced Study UESTC China University of Electronic Science and Technology of China UESTC School of Computer Science and Technology Chengdu China Tongji University Shanghai China

Existing Unbiased Scene Graph Generation (USGG) methods only focus on addressing the predicate-level imbalance that high-frequency classes dominate predictions of rare ones, while overlooking the concept-level imbalance. Actually, even if predicates themselves are balanced, there is still a significant concept-imbalance within them due to the long-tailed distribution of contexts (i.e., subject-object combinations). This concept-level imbalance poses a more pervasive and challenging issue compared to the predicate-level imbalance since subject-object pairs are inherently complex in combinations. To address the issue, we propose Multi-Concept Learning (MCL), a novel concept-level balanced learning framework orthogonal to existing SGG methods. MCL first quantifies the concept-level imbalance across predicates in terms of different amounts of concepts, representing as multiple concept-prototypes within the same class. Then, to achieve balanced learning across different concepts (i.e., concept-prototypes), we introduce the Concept-based Balanced Memory (CBM), which guides SGG models in generating balanced representations for concept-prototypes. Furthermore, the Concept Regularization (CR) technique is proposed to effectively help models in aligning relation features to their corresponding concept-prototypes, thereby generating concept-level compact and predicate-level distinctive representations for robust relation recognition. Finally, we introduce a novel metric, mean Context Recall (mCR@K), as a complement to mean Recall (mR@K), to evaluate the model's performance across concepts (determined by contexts) within the same predicate. Extensive experiments demonstrate the remarkable efficacy of our model-agnostic strategy in enhancing the performance of benchmark models on both VG-SGG and OI-SGG datasets, leading to new state-of-the-art achievements in two key aspects: predicate-level unbiased relation recognition and concept-level compositional generability. © 1992-2012

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Virtual Viewpoint Rendering Method Based on Multi-Threshold Layering 8

Virtual Viewpoint Rendering Method Based on Multi-Threshold ...

引用

8th International Conference on Image, Vision and Computing, ICIVC 2023

作者： Wang, Jiahe Liu, Jiayue School of Computer Beijing Institute of Technology Beijing China School of Materials Science and Engineering Beijing Institute of Technology Beijing China

ISBN: (纸本)9798350335231

In order to solve the problem of artifacts and holes in virtual viewpoint rendering, this paper proposes a virtual viewpoint rendering method based on multi-threshold layering. The processing flow of the method is divided into two algorithms, the pre-algorithm solves the artifact problem, and the post-algorithm solves the hole problem. In the pre-algorithm, the depth refinement and pixel correction parts produce precise pixel alignment between color and depth image pairs, eliminating contour artifacts, and then the color correction section eliminates color aberration artifacts. In the post-algorithm, the Otsu multi-threshold layering part separates the scene by layer, and combines with selected median filtering to eliminate crack holes. Then, the depth-guided hole filling part fills in occlusion holes and out-of-field holes based on pixel categories, improving the quality of the virtual view. Experiments have shown that our method performs better than many other methods in terms of subjective visual quality and objective evaluation. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Visible and near-infrared image fusion based on information complementarity

引用

CAAI Transactions on Intelligence technology 2025年第1期10卷 193-206页

作者： Zhuo Li Shiliang Pu Mengqi Ji Feng Zeng Bo Li The School of Computer Science and Engineering Beihang UniversityBeijingChina Hangzhou Hikvision Digital Technology Co. Ltd.HangzhouChina The School of Artificial Intelligence Beihang UniversityBeijingChina Hangzhou International Innovation Institute Beihang UniversityHangzhouChina

Images with complementary spectral information can be recorded using image sensors that can identify visible and near-infrared *** fusion of visible and nearinfrared(NIR)aims to enhance the quality of images acquired by video monitoring systems for the ease of user observation and data ***,current fusion algorithms produce artefacts and colour distortion since they cannot make use of spectrum properties and are lacking in information ***,an information complementarity fusion(ICF)model is designed based on physical *** order to separate high-frequency noise from important information in distinct frequency layers,the authors first extracted texture-scale and edge-scale layers using a two-scale ***,the difference map between visible and near-infrared was filtered using the extended-DoG filter to produce the initial visible-NIR complementary weight ***,to generate a guide map,the near-infrared image with night adjustment was processed as *** final complementarity weight map was subsequently derived via an arctanI function mapping using the guide map and the initial weight ***,fusion images were generated with the complementarity weight *** experimental results demonstrate that the proposed approach outperforms the state-of-the-art in both avoiding artificial colours as well as effectively utilising information complementarity.

关键词： color distortion image fusion information complementarity low light near-infrared

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning for Soil Moisture Estimation: A Case Study of the Tibetan Plateau 24

Ensemble Learning for Soil Moisture Estimation: A Case Study...

引用

6th International Conference on Image, Video and Signal Processing, IVSP 2024

作者： Hao, Xiang Wang, Liejun He, Lijun Li, Fan School Of Computer Science And Technology Xinjiang University Urumqi China School Of Information And Communications Engineering Xi'an Jiaotong University Xi'an China

ISBN: (纸本)9798400716829

Soil moisture (SM) plays a critical role in agriculture, water management, climate modeling, ecosystem health, and hazard prediction. The majority of SM estimation methods rely on individual machine learning models, which are less robust and more prone to underfitting or overfitting. To overcome the issue, we design SM estimation models based on ensemble learning. The land-surface temperature (LST) has been identified as the most influential indicator of SM in prior research. However, the MOD11A1 LST product suffers from significant data gaps, rendering it unsuitable for direct application in SM estimation. To incorporate the crucial indicator of LST in SM estimation, we employ Random Forest (RF) to impute the missing data in the MOD11A1 LST product. Subsequently, we develop an RF-based LST reconstruction and estimation by utilizing the imputed MOD11A1 LST product and in situ soil temperature measurements. Next, we construct separate SM estimation models based on Extra Tree (ERT) and Light Gradient Boosting Machine (LightGBM), respectively, using the reconstructed LST and in situ measured SM. Finally, to enhance the accuracy of SM estimation, we construct an EL-Stacking-based SM estimation model by combining predictions from ERT or LightGBM with in situ SM measurements. The results substantiate the superior performance of our proposed EL-Stacking methods compared to other models. The root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R) of EL-Stacking were 0.0349-0.0657m3m-3, 0.0227-0.0525m3m-3 and 0.7305-0.9657, respectively. Furthermore, EL-Stacking effectively captures spatial dynamics and exhibits stronger consistency with in situ measurements. © 2024 ACM.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach to Detect Fake News 17

Machine Learning Approach to Detect Fake News

引用

17th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2023

作者： Khare, Sakshi Singh, Pushpa Kumar, Pankaj Shrivastava, Rajesh Kumar Gl Bajaj Institute of Technology Department of Computer Science and Engineering Greater Noida India Bennett University School of Computer Science Engineering and Technology Greater Noida India

ISBN: (纸本)9798350307672

Social media is a powerful platform that allows users to share their thoughts, news, and a variety of information freely. Most people trust social media news and get affected by it. No one is sure about the content available on the social media. In this paper, we will target to detect whether the given content over social media is real or fake. Here, we applied various machine learning methods to label data and compare their accuracy. we achieved 99% accuracy, 99% precision, 99% recall, and 99f1score value as our experiment result © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Video Summarization using Speech Recognition and Text Summarization 4

Video Summarization using Speech Recognition and Text Summar...

引用

4th International Conference for Emerging technology, INCET 2023

作者： Tyagi, Tirath Dhari, Lakshaya Nigam, Yash Nagpal, Renuka Amity University Amity School of Engineering and Technology Department of Computer Science and Engineering Uttar Pradesh India

ISBN: (纸本)9798350335750

Videos on the internet have been increasingly becoming the chief source of knowledge and information in today's digital age. However, with increasing length of videos and diminishing time to spare in everyone's lives, a need has emerged for Video Summarization tools that can provide a good summary about the content of videos without the need to watch videos in their entirety. In this paper, we introduce a two-fold approach to fetch the subject matter of videos through effective summarization. The employed approach comprises of two phases: the first phase involves performing speech-to-text conversion using an Automatic Speech Recognition(ASR) system based on a Convolutional Neural Network(CNN) for generating respective transcripts for input videos while the second phase involves performing Extractive Text Summarization to summarize the text generated by extracting the important information. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Mobile Health Application for Proactive Self-management: A Case Study of Hypertensive Diabetic Patients in Thailand

引用

Journal of Mobile Multimedia 2025年第1期21卷 57-86页

作者： Sanon, Sutussa Temdee, Punnarumol Computer and Communication Engineering for Capacity Building Research Center School of Applied Digital Technology Mae Fah Luang University Chiang Rai Thailand

Diabetes and hypertension are prevalent chronic diseases globally. This study was conducted in Thailand and aimed to investigate the impact of a mobile application tailored for promoting self-management of hypertensive diabetic patients. The proposed mobile application provides users with the ability to monitor personal and clinical data and receive personal health recommendations. The recommendations are given according to the health condition trends and personal engagement level of the patient. Health condition detection was used to identify the trends, which can be positive, negative, or neutral progression trends. Personalized recommendations are provided to each patient by investigating personal engagement levels using associate rules. The proposed mobile application was evaluated in terms of effectiveness and user satisfaction for both healthcare professionals and patients in Thailand. The proposed mobile application was considered to be effective at a “moderately high” level (78%) according to 10 healthcare professionals and received an average score of 4.18 out of 5 (“very satisfied”) from 33 patients. © 2025 River Publishers.

关键词： association rule diabetes Hypertension mobile application patient modeling self-management

来源：评论

学校读者我要写书评

暂无评论

A Secure and Efficient Framework for Multi-Round Data Trading Over the Internet of Artificially Intelligent Things

引用

IEEE Internet of Things Magazine 2022年第1期5卷 119-124页

作者： Zheng, Xu Zhang, Lizong Hui, Bei Tian, Ling Cai, Zhipeng School of Computer Science and Engineering University of Electronic Science and Technology of China China School of Information and Software Engineering University of Electronic Science and Technology of China China Georgia State University Department of Computer Science United States

IoT data trading has greatly benefited the popularization of both the Internet of Things (IoT) and Artificial Intelligence of Things (AIoT). Current solutions mainly treat the dataset owned by each device as a commodity and focus on maintaining a data market. Meanwhile, inspired by recent achievements in distributed machine learning and federated learning, AIoT can actually realize its services by retaining the data locally on devices and only exchanging model parameters. However, existing IoT data trading methods fail to meet this secure and efficient process. Therefore, this article proposes a novel framework for data trading over AIoT. It allows the service provider to trade on deep learning model training instead of purchasing the full datasets. Key factors for the security issues and data pricing are addressed for the framework, including the design of the learning parameters and the comprehensive privacy concerns. Then a novel data trading strategy is proposed for the service provider to jointly maintain the model performance and the budget consumption. Evaluation results reveal the improvements on the model performance. Finally, some open problems in the design of data trading in AIoTs are discussed. © 2018 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Diverse Geographical Regions Based Biodiversity Conservation by LiDAR Image with Deep Learning Model

引用

Remote Sensing in Earth Systems Sciences 2024年第4期7卷 738-749页

作者： Babu C. N, Gireesh Reddy, Chilukala Mahender Kumar, Mungara Kiran Nagaraju, Komatigunta Maheswari, G. Uma Kiran, Ajmeera Department of Computer Science and Engineering BMS Institute of Technology & amp Management Karnataka Bengaluru India Department of Artificial Intelligence and Data Science GITAM (Deemed to be University) Hyderabad India Department of CSE School of Technology GITAM (Deemed to Be University) Hyderabad India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur Dist A.P India Department of Computer Science and Engineering RMK College of Engineering and Technology Pudhuvoyal Chennai India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Reliable data on the composition and structure of forests at various spatial scales is necessary for the conservation and monitoring of forest biodiversity. However, because field sampling techniques can be challenging, comprehensive data regarding the features of forest habitat over wide areas are frequently lacking. In order to get over this restriction, we created variables that describe the structure of the forest landscape over a wide environmental gradient using a nationally accessible light detection and ranging (LiDAR) remote sensing dataset. This research proposes a novel technique in forest management based on biodiversity analysis using LiDAR image processing by deep learning techniques. Here, the input LiDAR image has been collected as temperature pattern dataset in major deforestation regions and processed for noise removal and normalization. This image feature has been extracted using recurrent graph learning-based SegNet component analysis. Then, this extracted feature has been classified using Gaussian deep belief region-based adversarial neural networks. The experimental analysis has been carried out for various temperature pattern datasets in terms of random accuracy, average precision, recall, NSE, and AUC. The results of this study will help determine policy objectives for the restoration of mountain areas and enhance the effectiveness of monitoring damaged mountain forests. With the help of the suggested method, 96% random accuracy, 94% average precision, 49% NSE, 93% recall, and 95% AUC were achieved. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Adversarial neural networks Deep learning techniques Deforestation rate LiDAR image processing Temperature rise 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：