检索结果-内蒙古大学图书馆

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Baseera A Jobin M Scaria Abha Trivedi Mayank Sharma Preeti Sharma Preeti Saini School of Computing Science and Engineering VIT Bhopal University Sehore Madhya Pradesh India School Of Information Technology IBS University Port Moresby Papua New Guinea School of Computing Science Engineering and Artificial Intelligence VIT Bhopal University Bhopal Madhya Pradesh India School of Advanced Sciences and Languages VIT Bhopal University Bhopal Madhya Pradesh India Bansal College of Engineering Bhopal India Manav Rachna International Institute of Research and Studies Faridabad Haryana India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

Privacy protection is required when analyzing healthcare data and using it effectively. This work proposes a novel technique to secure private data in AI-powered medical systems while providing important data insights. The recommended method incorporates challenging techniques such as integrating Laplace distribution noise, managing secure data, and training group models. A privacy budget manages settings to balance analysis performance and individual contributions. The framework outperforms existing approaches in accuracy, precision, memory, F1 score, and privacy compliance. The technique improves data, models, training, and inference speeds, making it suitable for real-time healthcare applications. Iterative feedback enhances the model by modifying components based on real-world data. In addition to ensuring privacy, this entire design enables AI-powered medical systems to identify and anticipate findings. It provides a true, scalable solution that can adapt to healthcare demands, creating a new standard for AI app privacy and data usage. The technology provides a privacy-protected, highly efficient model that enhances decision-making and patient outcomes, enabling AI in healthcare.

关键词： Training Data privacy Privacy Noise Decision making Medical services Data models Real-time systems Iterative methods Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Blockchain Based Automatic Access Scheme Design and Implement for Small Cell Base Station 21

A Blockchain Based Automatic Access Scheme Design and Implem...

引用

21st IEEE International Conference on Communication technology, ICCT 2021

作者： Liang, Jingchao Wu, Jun Tan, Bin Ren, Haoqi Zhang, Zhifeng School of Computer Science and Technology Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China Fudan University School of Computer Science Shanghai China Jinggangshan University Electronics and Information Engineering Ji'an China Tongji University Electronics and Information Engineering Shanghai China

ISBN: (纸本)9781665432061

5G technology is constrained by its higher frequency band and smaller coverage area, which leads to the need for operators to use technologies such as small cell base stations to increase the density of base station deployment to ensure signal coverage quality, which leads to more enormous construction costs. Therefore, it is urgent to find a safe and reliable solution that can use the existing public network to realize small cell base stations with automatic access. Based on this demand, we summarize various existing small cell base station automatic access technology solutions and their advantages and disadvantages while combing the characteristics of blockchain technology and its application solutions in similar scenarios. And then, we propose a new blockchain-based base station automatic access solution and implements the system in a practical scenario. In our solution, we innovatively introduce blockchain as an intermediate manager for small base stations and core networks, which solves traditional solutions requiring customized equipment while ensuring safety and reliability. It reduces costs and improves efficiency, but some problems are brought by the 'decentralization' of blockchain waiting to be solved. © 2021 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Identifying temporary water bodies from drone images at real-time using deep-learning techniques

Identifying temporary water bodies from drone images at real...

引用

Advanced computing and Analytics (ACOMPA), International Conference on

作者： Hieu Minh Truong Manuel Clavel Computer Science Department Vietnamese-German University Binh Duong Vietnam School of Computing and Information Technology Eastern International University Binh Duong Vietnam

ISBN: (纸本)9781665461726

The detection and control of larval habitats—in particular, temporary water bodies—can play an important role in fighting against mosquito-transmitted diseases like malaria. In this paper, we explore the feasibility of identifying temporary water bodies from images taken by surveillance drones at real-time using the YOLOv4 algorithm. For our experiments, we use a dataset consisting of 782 drone-captured images, which includes 1522 temporary water bodies of different sizes and shapes, including puddles (i.e., small accumulations of water on a surface). Although still preliminary, our results are encouraging: the YOLOv4 trained models obtained a general score of 71.47(6.42)% mAP, and the processing time per image is 24.87 milliseconds, on average. In terms of size, the models can identify puddle objects as small as 23x23 cm on images taken from 120 m over surface-level.

关键词： Shape Surveillance Computational modeling Real-time systems Object recognition Surface treatment Drones

来源：评论

学校读者我要写书评

暂无评论

SED-MVS: Segmentation-Driven and Edge-Aligned Deformation Multi-View Stereo with Depth Restoration and Occlusion Constraint

arXiv

引用

arXiv 2025年

作者： Yuan, Zhenlong Yang, Zhidong Cai, Yujun Wu, Kuangxin Liu, Mufan Zhang, Dapeng Jiang, Hao Li, Zhaoxin Wang, Zhaoqi The Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Australia The Information Technology Department Hunan Police Academy Changsha410100 China Cooperative MediaNet Innovation Center Shanghai Jiao Tong University Shanghai200240 China DSLAB School of Information Science & Engineering Lanzhou University 730000 China Agricultural Information Institute Chinese Academy of Agricultural Sciences Key Laboratory of Agricultural Big Data Ministry of Agriculture and Rural Affairs 100081 China

Recently, patch-deformation methods have exhibited significant effectiveness in multi-view stereo owing to the deformable and expandable patches in reconstructing textureless areas. However, such methods primarily emphasize broadening the receptive field in textureless areas, while neglecting deformation instability caused by easily overlooked edge-skipping, potentially leading to matching distortions. To address this, we propose SED-MVS, which adopts panoptic segmentation and multi-trajectory diffusion strategy for segmentation-driven and edge-aligned patch deformation. Specifically, to prevent unanticipated edge-skipping, we first employ SAM2 for panoptic segmentation as depth-edge guidance to guide patch deformation, followed by multi-trajectory diffusion strategy to ensure patches are comprehensively aligned with depth edges. Moreover, to avoid potential inaccuracy of random initialization, we combine both sparse points from LoFTR and monocular depth map from DepthAnything V2 to restore reliable and realistic depth map for initialization and supervised guidance. Finally, we integrate segmentation image with monocular depth map to exploit inter-instance occlusion relationship, then further regard them as occlusion map to implement two distinct edge constraint, thereby facilitating occlusion-aware patch deformation. Extensive results on ETH3D, Tanks & Temples, BlendedMVS and Strecha datasets validate the state-of-the-art performance and robust generalization capability of our proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity Edge Detection 39

SAUGE: Taming SAM for Uncertainty-Aligned Multi-Granularity ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liufu, Xing Tan, Chaolei Lin, Xiaotong Qi, Yonggang Li, Jinxuan Hu, Jian-Fang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China

ISBN: (纸本)157735897X

Edge labels are typically at various granularity levels owing to the varying preferences of annotators, thus handling the subjectivity of per-pixel labels has been a focal point for edge detection. Previous methods often employ a simple voting strategy to diminish such label uncertainty or impose a strong assumption of labels with a pre-defined distribution, e.g., Gaussian. In this work, we unveil that the segment anything model (SAM) provides strong prior knowledge to model the uncertainty in edge labels. Our key insight is that the intermediate SAM features inherently correspond to object edges at various granularities, which reflects different edge options due to uncertainty. Therefore, we attempt to align uncertainty with granularity by regressing intermediate SAM features from different layers to object edges at multi-granularity levels. In doing so, the model can fully and explicitly explore diverse "uncertainties" in a data-driven fashion. Specifically, we inject a lightweight module (∼ 1.5% additional parameters) into the frozen SAM to progressively fuse and adapt its intermediate features to estimate edges from coarse to fine. It is crucial to normalize the granularity level of human edge labels to match their innate uncertainty. For this, we simply perform linear blending to the real edge labels at hand to create pseudo labels with varying granularities. Consequently, our uncertainty-aligned edge detector can flexibly produce edges at any desired granularity (including an optimal one). Thanks to SAM, our model uniquely demonstrates strong generalizability for cross-dataset edge detection. Extensive experimental results on BSDS500, Muticue and NYUDv2 validate our model’s superiority. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DTR: A Unified Deep Tensor Representation Framework for Multimedia Data Recovery

arXiv

引用

arXiv 2024年

作者： Zhou, Ting-Wei Zhao, Xi-Le Wang, Jian-Li Luo, Yi-Si Wang, Min Bai, Xiao-Xuan Yan, Hong The School of Mathematical Sciences Research Center for Image and Vision Computing University of Electronic Science and Technology of China Sichuan Chengdu611731 China The School of Computing and Artificial Intelligence Southwest Jiaotong University Sichuan Chengdu611756 China The School of Mathematics and Statistics Xi’an Jiaotong University Xi’an710049 China The School of Information Management Jiangxi University of Finance and Economics Jiangxi Nanchang330013 China The Glasgow College University of Electronic Science and Technology of China Sichuan Chengdu611731 China The Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong

Recently, the transform-based tensor representation has attracted increasing attention in multimedia data (e.g., images and videos) recovery problems, which consists of two indispensable components, i.e., transform and characterization. Previously, the development of transform-based tensor representation mainly focuses on the transform aspect. Although several attempts consider using shallow matrix factorization (e.g., singular value decomposition and negative matrix factorization) to characterize the frontal slices of transformed tensor (termed as latent tensor), the faithful characterization aspect is underexplored. To address this issue, we propose a unified Deep Tensor Representation (termed as DTR) framework by synergistically combining the deep latent generative module and the deep transform module. Especially, the deep latent generative module can faithfully generate the latent tensor as compared with shallow matrix factorization. The new DTR framework not only allows us to better understand the classic shallow representations, but also leads us to explore new representation. To examine the representation ability of the proposed DTR, we consider the representative multidimensional data recovery task and suggest an unsupervised DTR-based multi-dimensional data recovery model. Extensive experiments demonstrate that DTR achieves superior performance compared to state-of-the-art methods in both quantitative and qualitative aspects, especially for fine details recovery. Copyright © 2024, The Authors. All rights reserved.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Design of Named Entity Recognition Model for Awingi Language Using Deep Learning Approach

Design of Named Entity Recognition Model for Awingi Language...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Abebe Belew Kassahun Eshetie Derb Amogne Andualem Ayalew Ayodeji Olalekan Salau Sepiribo Lucky Braide Murtala Aminu Buhari Teaching Learning and Technology Team Leader ICT Executive Injibara University Injibara Ethiopia Department of Information Technology School of Computing Institute of Technology Debre Markos University Debre Markos Ethiopia Department of Information System College of Engineering and Technology Injibara University Injibara Ethiopia Department of Electrical/Electronics and Computer Engineering Afe Babalola University Ado-Ekiti Nigeria Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Rivers State University Port Harcourt Nigeria School of Science Engineering & Environment University of Salford United Kingdom

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

Named entity recognition is a field of NLP that aims to detect and extract relevant information from unstructured text documents. However, some Ethiopian languages were getting started in different research fields. One of the languages spoken in Ethiopia is called Awingi language has a rich morphology and it is highly lacking in computational linguistic tools. There is some NER research done in Ethiopian language using different approaches and classification techniques, but since there was a lack of study conducted on NER for the Awingi language. This study aims to design a named entity recognition model for the Awngi Language using a deep learning approach with word2vect word embedding techniques. The data collected from AMICO Hiber Awiꬼgi program was posted on social media pages, Awngi Language and Literature Department of Injibara University, and Awi Zone Educational and Training Department. Therefore, the study uses a newly tagged dataset with 37,133 tokens. Presently, researchers focused on discovering four main named entities such as persons, locations, Dates, and organizations from unstructured Awiꬼgi text by using the three algorithms namely convolutional neural networks, long short-term memory, and bi-directional long-short-term memory. For the feature engineering task, Word2vec and one-hot encoding are utilized. To identify the best-performing model, the researchers have conducted several experiments. Over other algorithms, the Bi-LSTM algorithm before sampling and word embedding performed better results, i.e 95.4%, 92.4%, 95.3%, and 91.2% Accuracy, precision, recall, and f1-score, respectively, and after sampling and word embedding it performed with 99.4%, 97.3%, 99.2%, and 97.2% Accuracy, precision, recall, and f1-score, respectively.

关键词： Deep learning Training Humanities Accuracy Social networking (online) Morphology Named entity recognition Organizations Encoding Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Usability and Aesthetics: Better Together for Automated Repair of Web Pages

Usability and Aesthetics: Better Together for Automated Repa...

引用

International Symposium on Software Reliability Engineering (ISSRE)

作者： Thanh Le-Cong Xuan Bach D. Le Quyet Thang Huynh Phi Le Nguyen School of Information and Communication Technology Hanoi University of Science and Technology Hanoi Vietnam School of Computing and Information Systems University of Melbourne Melbourne Australia

ISBN: (纸本)9781665425889

With the recent explosive growth of mobile devices such as smartphones or tablets, guaranteeing consistent web appearance across all environments has become a significant problem. This happens simply because it is hard to keep track of the web appearance on different sizes and types of devices that render the web pages. Therefore, fixing the inconsistent appearance of web pages can be difficult, and the cost incurred can be huge, e.g., poor user experience and financial loss due to it. Recently, automated web repair techniques have been proposed to automatically resolve inconsistent web page appearance, focusing on improving usability. However, generated patches tend to disrupt the webpage's layout, rendering the repaired webpage aesthetically unpleasing, e.g., distorted images or misalignment of components. In this paper, we propose an automated repair approach for web pages based on meta-heuristic algorithms that can assure both usability and aesthetics. The key novelty that empowers our approach is a novel fitness function that allows us to optimistically evolve buggy web pages to find the best solution that optimizes both usability and aesthetics at the same time. Empirical evaluations show that our approach is able to successfully resolve mobile-friendly problems in 94% of the evaluation subjects, significantly outperforming state-of-the-art baseline techniques in terms of both usability and aesthetics.

关键词： Layout Pipelines Web pages Maintenance engineering Rendering (computer graphics) User experience Software

来源：评论

学校读者我要写书评

暂无评论

De-END: Decoder-driven Watermarking Network

arXiv

引用

arXiv 2022年

作者： Fang, Han Jia, Zhaoyang Qiu, Yupeng Zhang, Jiyi Zhang, Weiming Chang, Ee-Chien School of Computing National University of Singapore Singapore CAS Key Laboratory of Electromagnetic Space Information University of Science and Technology of China Hefei230026 China

With recent advances in machine learning, researchers are now able to solve traditional problems with new solutions. In the area of digital watermarking, deep-learning-based watermarking technique is being extensively studied. Most existing approaches adopt a similar encoder-driven scheme which we name END (Encoder-NoiseLayer-Decoder) architecture. In this paper, we revamp the architecture and creatively design a decoder-driven watermarking network dubbed De-END which greatly outperforms the existing END-based methods. The motivation for designing De-END originated from the potential drawback we discovered in END architecture: The encoder may embed redundant features that are not necessary for decoding, limiting the performance of the whole network. We conducted a detailed analysis and found that such limitations are caused by unsatisfactory coupling between the encoder and decoder in END. De-END addresses such drawbacks by adopting a Decoder-Encoder-Noiselayer-Decoder architecture. In De-END, the host image is firstly processed by the decoder to generate a latent feature map instead of being directly fed into the encoder. This latent feature map is concatenated to the original watermark message and then processed by the encoder. This change in design is crucial as it makes the feature of encoder and decoder directly shared thus the encoder and decoder are better coupled. We conducted extensive experiments and the results show that this framework outperforms the existing state-of-the-art (SOTA) END-based deep learning watermarking both in visual quality and robustness. On the premise of the same decoder structure, the visual quality (measured by PSNR) of De-END improves by 1.6dB (45.16dB → 46.84dB), and extraction accuracy after JPEG compression (QF=50) distortion outperforms more than 4% (94.9% → 99.1%). Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Verifying ReLU Neural Networks from a Model Checking Perspective

引用

Journal of Computer science & technology 2020年第6期35卷 1365-1381页

作者： Wan-Wei Liu Fu Song Tang-Hao-Ran Zhang Ji Wang College of Computer Science National University of Defense TechnologyChangsha 410073China School of Information Science and Technology ShanghaiTech UniversityShanghai 201210China Shanghai Engineering Research Center of Intelligent Vision and Imaging Shanghai 201210China State Key Laboratory for High Performance Computing Changsha 410073China

Neural networks, as an important computing model, have a wide application in artificial intelligence (AI) domain. From the perspective of computer science, such a computing model requires a formal description of its behaviors, particularly the relation between input and output. In addition, such specifications ought to be verified automatically. ReLU (rectified linear unit) neural networks are intensively used in practice. In this paper, we present ReLU Temporal Logic (ReTL), whose semantics is defined with respect to ReLU neural networks, which could specify value-related properties about the network. We show that the model checking algorithm for theΣ2∪Π2 fragment of ReTL, which can express properties such as output reachability, is decidable in EXPSPACE. We have also implemented our algorithm with a prototype tool, and experimental results demonstrate the feasibility of the presented model checking approach.

关键词： model checking rectified linear unit neural(ReLU)network temporal logic

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：