检索结果-内蒙古大学图书馆

TechRxiv 2023年

作者： Rekavandi, Aref Miri Boussaid, Farid Seghouane, Abd-Krim Bennamoun, Mohammed The Department of Computer Science and Software Engineering The University of Western Australia 35 Stirling Highway CrawleyWA6009 Australia The Department of Electrical Electronics and Computer Engineering The University of Western Australia 35 Stirling Highway CrawleyWA6009 Australia School of Mathematics and Statistics The University of Melbourne Melbourne Australia

Camera pose estimation has long relied on geometry-based approaches and sparse 2D-3D keypoint correspondences. With the advent of deep learning methods, the estimation of camera pose parameters (i.e., the six parameters that describe position and rotation) has decreased from tens of meters to a few centimeters in median error for indoor applications. For outdoor applications, errors can be quite large and highly dependent on the levels of variations in occlusion, contrast, brightness, repetitive structures, or blur introduced by camera motion. To address these limitations, we introduce, B-Pose, a Bayesian Convolutional deep network capable of not only automatically estimating the camera’s pose parameters from a single RGB image but also providing a measure of uncertainty in the parameter estimation. Reported experiments on outdoor and indoor datasets demonstrate that B-Pose outperforms SOTA techniques and generalizes better to unseen RGB images. A strong correlation is shown between the prediction error and the model’s uncertainty, indicating that the prediction is almost always incorrect whenever the model’s uncertainty is high. © 2023, CC BY-NC-SA.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Enhancing Robust Text Classification via Category Description

Enhancing Robust Text Classification via Category Descriptio...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Xin Gao Zhengye Zhu Xu Chu Yasha Wang Wenjie Ruan Junfeng Zhao Key Lab of High Confidence Software Technologies Ministry of Education School of Computer Science Peking University School of Computer Science Peking University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China National Engineering Research Center of Software Engineering Peking University Beijing China University of Exeter Exeter UK

Despite the success of deep neural networks on text classification, their large capacity also leads to capturing task-irrelevant patterns such as label noise. Label noise is usually introduced into the data during label collection and causes nontrivial declines in performance due to the memorization effect. Though effort has been devoted to combating the label noise in other systems such as image classification, high-quality input features are necessary for discovering task-relevant patterns before memorizing the label noise. However, such a high-quality input feature requirement is hard to be satisfied for text classification due to the nature of natural language. To combat the label noise with low-quality input features in the text classification, we propose a novel framework that exploits external category descriptions to construct prototypes that can be used to denoise the input representation and alleviate the over-fitting. However, there still remains a challenge that the external category descriptions from other corpora could be semantically discrepant with the underlying task-specific classes in the training corpus. To align their semantics, we propose two regularizers that penalize sample-wise semantic-based deviations at the local level and class-wise structure-based deviations at the global level, respectively. Our extensive experiments across two open datasets and one real-world case study demonstrate that our method is superior to state-of-the-art baselines under various settings of label noise.

关键词： Training Deep learning Text categorization Semantics Neural networks Natural languages Prototypes

来源：评论

学校读者我要写书评

暂无评论

Mixture of Knowledge Minigraph Agents for Literature Review Generation 39

Mixture of Knowledge Minigraph Agents for Literature Review ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Zhi Liu, Yan Zhong, Sheng-Hua Chen, Gong Yang, Yu Cao, Jiannong The Hong Kong Polytechnic University Department of Computing 999077 Hong Kong Shenzhen University College of Computer Science and Software Engineering Guangdong Shenzhen518052 China The Education University of Hong Kong Centre for Learning Teaching and Technology 999077 Hong Kong

ISBN: (纸本)157735897X

Literature reviews play a crucial role in scientific research for understanding the current state of research, identifying gaps, and guiding future studies on specific topics. However, the process of conducting a comprehensive literature review is yet time-consuming. This paper proposes a novel framework, collaborative knowledge minigraph agents (CKMAs), to automate scholarly literature reviews. A novel prompt-based algorithm, the knowledge minigraph construction agent (KMCA), is designed to identify relations between concepts from academic literature and automatically constructs knowledge minigraphs. By leveraging the capabilities of large language models on constructed knowledge minigraphs, the multiple path summarization agent (MPSA) efficiently organizes concepts and relations from different viewpoints to generate literature review paragraphs. We evaluate CKMAs on three benchmark datasets. Experimental results show the effectiveness of the proposed method, further revealing promising applications of LLMs in scientific research. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

The Original Method of Controlling a computer Using Distance Sensors 16

The Original Method of Controlling a Computer Using Distance...

引用

16th IEEE International Conference on Advanced Trends in Radioelectronics, Telecommunications and computer engineering, TCSET 2022

作者： Savaryn, Pavlo Strekha, Vadym Brych, Mykola Brych, Lesia Kabak, Vitalii Polishchuk, Mykola Lutsk National Technical University Department of Digital Education Technologies Lutsk Ukraine Lutsk National Technical University Department of Computer Science Lutsk Ukraine Internet of Things and Software Defined Networks Lab Lviv Polytechnic National University Lviv Ukraine Centre for International Education Lviv Polytechnic National University Lviv Ukraine Lutsk National Technical University Department of Computer Engineering and Cybersecurity Lutsk Ukraine

ISBN: (纸本)9781665468619

The article provides a brief overview of human-computer interaction methods and systems, and the research made in this area. We have designed the architecture of the system and tested a method of controlling a computer using ultrasonic distance sensors. In the course of the experiment, the following problems have been solved: obtaining and processing data from several distance sensors, data transfer to gesture recognition algorithm, uncontrolled oscillations of sensor indicators. The suggested method of controlling a computer can be used in ubiquitous computing. © 2022 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Comparison of Multi-Phase Power Converters and Power Delivery Networks for Next-Generation Space Architectures

Comparison of Multi-Phase Power Converters and Power Deliver...

引用

IEEE Conference on Aerospace

作者： Nicholas Franconi Thomas Cook Christopher Wilson Alan D. George NASA Goddard Space Flight Center Science Data Processing Branch Code 587 Software Engineering Division Department of Electrical and Computer Engineering NSF Center for Space High-Performance and Resilient Computing (SHREC) University of Pittsburgh

Next-generation spacecraft developers are earnestly investigating the application of artificial intelligence (AI) algorithms onboard to enable new mission concepts for space exploration and science. However, the current generation of radiation-hardened processors are inferior compared to commercial-off-the-shelf alternatives in terms of the computational performance required by modern AI applications. To address this disparity, space-system designers have started employing novel radiation-tolerant architectures combining both commercial and radiation-hardened components to mitigate radiation effects at a system level. Unfortunately, developing single-board computers with radiation-tolerant, high-performance processors is challenging because designers must balance the sparce selection of radiation-hardened power converters and high-reliability decoupling capacitors with SmallSat/CubeSat area constraints and limited thermal conduction. Consequently, the next-generation of space processors, including the AMD-Xilinx Versal Adaptive Compute Acceleration Platform require demanding power solutions capable of supplying core rails with 0.8V ± 18mV and currents up to 150 A. In this paper, we present a multifaceted analysis of the power system and decoupling network for a future Versal-based design. We developed preliminary power estimates based on expected processor and FPGA resource utilization for common AI processing applications. These estimates drive the power system requirements and a comparative analysis of single-phase integrated converters and multi-phase discrete converters for high-current FPGA supplies. We develop a tradespace between the number of phases, input voltage, load current, switching frequency, power efficiency, and printed circuit board area. Finally, we design and simulate four power delivery networks based on commercial, high-reliability, and flight-qualified capacitors to compare the efficacy of 0201 decoupling capacitors in flight missions.

关键词： Rails Program processors Capacitors Voltage Power systems Resource management Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Towards Instant Clustering Approach for Federated Learning Client Selection

Towards Instant Clustering Approach for Federated Learning C...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Sarhad Arisdakessian Omar Abdel Wahab Azzam Mourad Hadi Otrok Department of Computer and Software Engineering Polytechnique Montréal Montréal Canada Department of Computer Science Lebanese American University Beirut Lebanon Division of Science New York University Abu Dhabi UAE Department of EECS Center of Cyber-Physical Systems (C2PS) Khalifa University Abu Dhabi UAE

In just few years, Federated Learning (FL) started to gain unprecedented attention given its ability to solve some fundamental privacy and communication challenges of traditional machine learning. Client selection is one of the main challenges in FL and is usually done in a random fashion, where the central server arbitrarily selects a certain number of clients to participate in each training round. However, given the heterogeneity of the client devices in terms of data quality and resource availability, randomly selecting clients is likely to result in long local training time and thus delayed global model’s convergence. To address this problem, in this work, we propose a real-time and on-demand client selection mechanism that employs the DBSCAN (Density-Based Spatial clustering of Applications with Noise) clustering technique from machine learning to group the clients into a set of homogeneous clusters based on a set of criteria defined by the FL task owners, such as resource availability, data quality, data size, data freshness and non-IID degree. Based on the requirements of each FL task, the server then intelligently selects the clusters of clients that best match with each task’s requirements, thus improving the performance of the overall federated learning process. Experiments suggest that our solution significantly improves the accuracy of FL compared to the Vanilla FL approach.

关键词： Training Privacy Federated learning Data integrity Clustering algorithms Real-time systems Data models

来源：评论

学校读者我要写书评

暂无评论

Nanoinformatics: Opportunities and challenges in the development and delivery of healthcare products in developing countries 4

Nanoinformatics: Opportunities and challenges in the develop...

引用

4th International Conference on science and Sustainable Development: Advances in sciences and Technology for Sustainable Development, ICSSD 2020

作者： Nwankwo, Wilson Ukhurebor, Kingsley Eghonghon Software Engineering and Cyberphysical Systems Unit Department of Computer Science Edo University Iyamho Edo State Nigeria Environmental AndTelecommunication Unit Department of Physics Edo University Iyamho Edo State Nigeria

The world is witnessing sustained effects of information technologies across all works of life. Though some of these influences are markedly negative and detrimental to the socio-economic prospects and progress of the society, the positive effects are often impressive especially where they are integrated for the betterment and greater good of the larger society. One of the fastest growing technologies is nanotechnology. Nanotechnology has numerous prospects and applicability across various sectors ranging from electronics, telecommunications, agriculture and food production, biotechnology and genetics, oil prospecting and production, remote sensing, drug production, to name a few. This novel technology readily finds usefulness and several researches are ongoing, geared at developing new tools and techniques that would improve its acceptance across the concerned domains. It is this quest that has culminated into the ongoing effort in nanoinformatics, an interdisciplinary study and a subdomain of informatics simply regarded as the conscientious application of informatics tools and technologies to the analysis, design and development of systems on the broad spectrum of nanomaterials including their physicochemical and environmental characteristics as well as their interactions, interrelationships, and applications within a given domain. This paper presents a review of some opportunities for individuals, experts, and the society especially in the production of cost-effective nanotechnology-based healthcare products. Notwithstanding the aforesaid opportunities which could be harnessed and sustained in any developing country like Nigeria, this paper identifies and buttresses core challenges that could confront the adoption of good nanoinformatics methodologies. This paper concludes that a developing country (Nigeria in perspective) could benefit from nanoinformatics if there are stronger ties among the key stakeholders involved in healthcare products delivery in the socie

关键词： Developing countries

来源：评论

学校读者我要写书评

暂无评论

Data-Aware Gradient Compression for FL in Communication-Constrained Mobile Computing

arXiv

引用

arXiv 2023年

作者： Lu, Rongwei Jiang, Yutong Mao, Yinan Tang, Chen Chen, Bin Cui, Laizhong Wang, Zhi Shenzhen International Graduate School Tsinghua University Shenzhen518000 China The AI Cloud Business Group Baidu Incorporated Beijing100085 China The Department of Computer Science and Technology Tsinghua University Beijing100084 China The Department of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

Federated Learning (FL) in mobile environments faces significant communication bottlenecks. Gradient compression has proven as an effective solution to this issue, offering substantial benefits in environments with limited bandwidth and metered data. Yet, it encounters severe performance drops in non-IID environments due to a one-size-fits-all compression approach, which does not account for the varying data volumes across workers. Assigning varying compression ratios to workers with distinct data distributions and volumes is therefore a promising solution. This work derives the convergence rate of distributed SGD with non-uniform compression, which reveals the intricate relationship between model convergence and the compression ratios applied to individual workers. Accordingly, we frame the relative compression ratio assignment as an n-variable chi-squared nonlinear optimization problem, constrained by a limited communication budget. We propose DAGC-R, which assigns conservative compression to workers handling larger data volumes. Recognizing the computational limitations of mobile devices, we propose the DAGC-A, which is computationally less demanding and enhances the robustness of compression in non-IID scenarios. Our experiments confirm that the DAGC-R and DAGC-A can speed up the training speed by up to 25.43% and 16.65% compared to the uniform compression respectively, when dealing with highly imbalanced data volume distribution and restricted communication. © 2023, CC BY-NC-SA.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization

arXiv

引用

arXiv 2023年

作者： Qiu, Zi-Hao Hu, Quanqi Yuan, Zhuoning Zhou, Denny Zhang, Lijun Yang, Tianbao National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Computer Science and Engineering Texas A&M University College Station United States Department of Computer Science The University of Iowa Iowa City United States Google Research United States

In this paper, we aim to optimize a contrastive loss with individualized temperatures in a principled and systematic manner for self-supervised learning. The common practice of using a global temperature parameter τ ignores the fact that "not all semantics are created equal", meaning that different anchor data may have different numbers of samples with similar semantics, especially when data exhibits long-tails. First, we propose a new robust contrastive loss inspired by distributionally robust optimization (DRO), providing us an intuition about the effect of τ and a mechanism for automatic temperature individualization. Then, we propose an efficient stochastic algorithm for optimizing the robust contrastive loss with a provable convergence guarantee without using large mini-batch sizes. Theoretical and experimental results show that our algorithm automatically learns a suitable τ for each sample. Specifically, samples with frequent semantics use large temperatures to keep local semantic structures, while samples with rare semantics use small temperatures to induce more separable features. Our method not only outperforms prior strong baselines (e.g., SimCLR, CLIP) on unimodal and bimodal datasets with larger improvements on imbalanced data but also is less sensitive to hyper-parameters. To our best knowledge, this is the first methodical approach to optimizing a contrastive loss with individualized temperatures. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SER Analysis -An Approach to enhance Human Health

SER Analysis -An Approach to enhance Human Health

引用

Data Intelligence and Cognitive Informatics (ICDICI), International Conference on

作者： Anusha N C.M. Mohana Akshat Sharma Aryan Sharma Garv Mittal Navadhesh. M Department of IoT School of Computer Science and Engineering (SCOPE) Vellore Institute of Technology Vellore TamilNadu India Department of Software Systems SCOPE Vellore Institute of Technology Vellore Tamil Nadu India Department of Computational Intelligence SCOPE Vellore Institute of Technology Vellore Tamil Nadu India

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

This work focuses on Speech Emotion Recognition (SER) for extracting emotional states from speech signals, encompassing universal emotions like Happiness, Anger, Neutral, Calm, Sadness, Disgust, Fearful, and Surprised. The methodology involves extracting features such as Chromogram, Mel- frequency cepstral coefficients (MFCC), Mel scaled spectrogram, Tonal Centroid and Spectral contrast, followed by classification using Artificial Neural Networks (ANN). A health-oriented aspect, is integrated in this model by providing personalized guided meditation sessions based on the user's emotional state to promote mental wellness. The main aim of this work is to broaden its reach and impact through ongoing refinement of the model and exploration of new implementation strategies, ultimately contributing to a healthier and happier society. The results of this work demonstrate promising accuracy, with the trained deep neural network (DNN) model achieving approximately 81.25% accuracy in recognizing speech emotions in comparison with the existing algorithms. DNN shows a 11%, 8%, 14% increase in accuracy with RNN & LSTM, SVM, GMM respectively.

关键词： Support vector machines Emotion recognition Accuracy Speech recognition Speech enhancement Feature extraction Cognitive informatics Mel frequency cepstral coefficient Spectrogram Long short term memory

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：