检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Han, Meng Wang, Liang Xiao, Limin Zhang, Hao Zhang, Chenhao Xie, Xilong Zheng, Shuai Dong, Jin State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Academy of Blockchain and Edge Computing China

Point cloud analytics has become a critical workload for embedded and mobile platforms across various applications. Farthest point sampling (FPS) is a fundamental and widely used kernel in point cloud processing. However, the heavy external memory access makes FPS a performance bottleneck for real-time point cloud processing. Although bucket-based farthest point sampling can significantly reduce unnecessary memory accesses during the point sampling stage, the KD-tree construction stage becomes the predominant contributor to execution time. In this paper, we present FuseFPS, an architecture and algorithm co-design for bucket-based farthest point sampling. We first propose a hardware-friendly sampling-driven KD-tree construction algorithm. The algorithm fuses the KD-tree construction stage into the point sampling stage, further reducing memory accesses. Then, we design an efficient accelerator for bucket-based point sampling. The accelerator can offload the entire bucket-based FPS kernel at a low hardware cost. Finally, we evaluate our approach on various point cloud datasets. The detailed experiments show that compared to the state-of-the-art accelerator QuickFPS, FuseFPS achieves about 4.3× and about 6.1× improvements on speed and power efficiency, respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

SP-Net: A Sparse Convolution and Point-Encoding Enhanced Network for 3D Object Detection in LiDAR Point Clouds

SP-Net: A Sparse Convolution and Point-Encoding Enhanced Net...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Meng Liu Jianwei Niu Yu Liu China North Artificial Intelligence and Innovation Research Institute Beijing China China North Vehicle Research Institute Beijing China State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China

LiDAR 3D object detection for autonomous driving is an important issue. To address this issue, this paper provides a two-stage anchor-based solution. Firstly, voxel feature encoding and sparse convolution networks were employed for proposal generation. Secondly, we performed voxel feature aggregation and hierarchical feature learning in combination with the proposals, multi-level and multiscale voxel features, point encoding and voxel-wise ROI pooling. The aggregated object-wise voxel features were utilized to refine the proposals. Extensive experiments were conducted on three challenging datasets: KITTI, nuScenes and Waymo. Experimental results demonstrated that our SP-Net can effectively achieve multi-category 3D object detection in diverse scenarios offering satisfactory accuracy and speed (28.6 FPS).

关键词：

来源：评论

学校读者我要写书评

暂无评论

K-B2S+: A one-dimensional CNN model for AF detection with short single-lead ECG waves from wearable devices

引用

Digital Communications and Networks 2025年第3期11卷 613-621页

作者： Bo Fang Zhaocheng Yu Li-bo Zhang Yue Teng Junxin Chen School of Computer Science University of Sydney NSW 2008 Australia College of Medicine and Biological Information Engineering Northeastern University Shenyang 110004 China Department of Radiology General Hospital of the Northern Theater of the Chinese People's Liberation Army Shenyang 110004 China School of Software Dalian University of Technology Dalian 116621 China

Wearable signal analysis is an important technology for monitoring physiological signals without interfering with an individual's daily behavior. As detecting cardiovascular diseases can dramatically reduce mortality, arrhythmia recognition using ECG signals has attracted much attention. In this paper, we propose a single-channel convolutional neural network to detect Atrial Fibrillation (AF) based on ECG signals collected by wearable devices. It contains 3 primary modules. All recordings are firstly uniformly sized, normalized, and Butterworth low-pass filtered for noise removal. Then the preprocessed ECG signals are fed into convolutional layers for feature extraction. In the classification module, the preprocessed signals are fed into convolutional layers containing large kernels for feature extraction, and the fully connected layer provides probabilities. During the training process, the output of the previous pooling layer is concatenated with the vectors of the convolutional layer as a new feature map to reduce feature loss. Numerous comparison and ablation experiments are performed on the 2017 PhysioNet/CinC Challenge dataset, demonstrating the superiority of the proposed method.

关键词： Single-lead ECG Wearable devices Feature concatenating Atrial fibrillation

来源：评论

学校读者我要写书评

暂无评论

Prediction of cutting power and surface quality, and optimization of cutting parameters using new inference system in high-speed milling process

引用

Advances in Manufacturing 2021年第3期9卷 388-402页

作者： Long-Hua Xu Chuan-Zhen Huang Jia-Hui Niu Jun Wang Han-Lian Liu Xiao-Dan Wang Center for Advanced Jet Engineering Technologies Key Laboratory of High-efficiency and Clean Mechanical Manufacture(Ministry of Education)National Experimental Teaching Demonstration Center for Mechanical Engineering(Shandong University)School of Mechanical EngineeringShandong UniversityJinanPeople’s Republic of China School of Mechanical and Manufacturing Engineering The University of New South Wales(UNSW)SydneyNSW2052Australia Department of Computer Science and Software Engineering Xi’an Jiaotong-Liverpool UniversitySuzhou215123JiangsuPeople’s Republic of China

During the actual high-speed machining process,it is necessary to reduce the energy consumption and improve the machined surface ***,the appropriate prediction models and optimal cutting parameters are difficult to obtain in complex machining ***,a novel intelligent system is proposed for prediction and optimization.A novel adaptive neuro-fuzzy inference system(NANFIS)is proposed to predict the energy consumption and surface *** the NANFIS model,the membership functions of the inputs are expanded into:membership superior and membership *** membership functions are varied based on the machining *** inputs of the NANFIS model are cutting parameters,and the outputs are the machining *** optimization,the optimal cutting parameters are obtained using the improved particle swarm optimization(IPSO)algorithm and NANFIS ***,the IPSO algorithm as a learning algorithm is used to train the NANFIS *** proposed intelligent system is applied to the high-speed milling process of compacted graphite *** experimental results show that the predictions of energy consumption and surface roughness by adopting the NANFIS models are up to 91.2%and 93.4%,*** NANFIS models can predict the energy consumption and surface roughness more accurately compared with other intelligent *** on the IPSO algorithm and NANFIS models,the optimal cutting parameters are obtained and validated to reduce both the cutting power and surface roughness and improve the milling *** is demonstrated that the proposed intelligent system is applicable to actual high-speed milling processes,thereby enabling sustainable and intelligent manufacturing.

关键词： Novel adaptive neuro-fuzzy inference system(NANFIS)model Improved particle swarm optimization(IPSO)algorithm Energy consumption Surface roughness Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

On the Noise Robustness of In-Context Learning for Text Generation

arXiv

引用

arXiv 2024年

作者： Gao, Hongfu Zhang, Feipeng Jiang, Wenyu Shu, Jun Zheng, Feng Wei, Hongxin Department of Statistics and Data Science Southern University of Science and Technology China School of Economics and Finance Xi’an Jiaotong University China National Key Laboratory for Novel Software Technology Nanjing University China School of Mathematics and Statistics Xi’an Jiaotong University China Department of Computer Science and Engineering Southern University of Science and Technology China

Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that in-context learning is robust to noisy demonstrations in text classification. In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning. To circumvent the issue, we propose a simple and effective approach called Local Perplexity Ranking (LPR), which replaces the "noisy" candidates with their nearest neighbors that are more likely to be clean. Our method is motivated by analyzing the perplexity deviation caused by noisy labels and decomposing perplexity into inherent perplexity and matching perplexity. Our key idea behind LPR is thus to decouple the matching perplexity by performing the ranking among the neighbors in semantic space. Our approach can prevent the selected demonstrations from including mismatched input-label pairs while preserving the effectiveness of the original selection methods. Extensive experiments demonstrate the effectiveness of LPR, improving the EM score by up to 18.75 on common benchmarks with noisy annotations. Our code is available at https://***/ml-stat-Sustech/Local-Perplexity-Ranking © 2024, CC0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel and Efficient Sequential Learning-Based Malware Classification Model

A Novel and Efficient Sequential Learning-Based Malware Clas...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Zine El Abidine Bensalem Ilyas Benkhaddra Mohamed Ali Setitra Mingyu Fan School of Computer Science and Engineering (Cyberspace Security) University of Electronic Science and Technology of China Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665493901

The proliferation and increasing sophistication of malicious programs and other security risks have been identified as the most significant problem of the modern cybersecurity age. Malicious software, named malware, carries out harmful operations, causing abnormal functioning, data leakage, and crippling financial effects. Therefore, the door is widely open for one of the most crucial realms, so-called deep learning-based malware classification techniques, to thwart malware attacks. Malware's structure evolves significantly over time, making detecting them challenging. Malware invokes API call sequences while executing, so call sequences from APIs make excellent candidates for features in malware classification. Different malware samples can contain API call sequences with lengths ranging from one to millions, which can raise computation costs and complicate processing times; selecting an efficient set of features is yet another challenge. Recurrent neural networks (RNNs) are one of the most adaptable techniques for handling time-series data and are used to classify malware based on API calls. To efficiently categorize malware, in this study, a novel and efficient Long Short Term Memory model has been designed and divided into eight categories: Adware, Backdoor, Downloader, Dropper, spyware, Trojan, Virus, and Worm. The achieved results in terms of recall, precision, and F1 values are notable across several classes, whereas the adware class has the most significant result with a recall value of 80%. The proposed LSTM-based method outperformed conventional methods with a weighted F1 score of 48%.

关键词： computers Recurrent neural networks Computational modeling Malware Trojan horses Spyware Long short term memory

来源：评论

学校读者我要写书评

暂无评论

How Mature is Requirements engineering for AI-based Systems? A Systematic Mapping Study on Practices, Challenges, and Future Research Directions

arXiv

引用

arXiv 2024年

作者： Umm-E-Habiba Haug, Markus Bogner, Justus Wagner, Stefan Institute of Software Engineering University of Stuttgart Stuttgart70569 Germany Department of Software Engineering University of Kotli Azad Jammu and Kashmir Azad Kashmir Kotli Pakistan Department of Computer Science Vrije Universiteit Amsterdam Amsterdam Netherlands TUM School of Communication Information and Technology Technical University of Munich Heilbronn Germany

Artificial intelligence (AI) permeates all fields of life, which resulted in new challenges in requirements engineering for artificial intelligence (RE4AI), e.g., the difficulty in specifying and validating requirements for AI or considering new quality requirements due to emerging ethical implications. It is currently unclear if existing RE methods are sufficient or if new ones are needed to address these challenges. Therefore, our goal is to provide a comprehensive overview of RE4AI to researchers and practitioners. What has been achieved so far, i.e., what practices are available, and what research gaps and challenges still need to be addressed? To achieve this, we conducted a systematic mapping study combining query string search and extensive snowballing. The extracted data was aggregated, and results were synthesized using thematic analysis. Our selection process led to the inclusion of 126 primary studies. Existing RE4AI research focuses mainly on requirements analysis and elicitation, with most practices applied in these areas. Furthermore, we identified requirements specification, explainability, and the gap between machine learning engineers and end-users as the most prevalent challenges, along with a few others. Additionally, we proposed seven potential research directions to address these challenges. Practitioners can use our results to identify and select suitable RE methods for working on their AI-based systems, while researchers can build on the identified gaps and research directions to push the field forward. ∗ © 2024, CC BY.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Efficient Joint Parameter Estimation and Soft Noncoherent Detection Scheme for LoRa-based IoT System

Efficient Joint Parameter Estimation and Soft Noncoherent De...

引用

Asia-Pacific Conference on Communications

作者： Zhongyang Yu Zhengying Wen Jixun Gao Yuqian Yan Chunhua Zhu School of Computer Science Henan University of Engineering Zhengzhou China School of Software Henan University of Engineering Zhengzhou China Key Laboratory of Grain Information Processing and Control (Henan University of Technology) Ministry of Education Zhengzhou China

Considering limited pilot overhead and large delay and Doppler shift in LoRa (Long Range)-based IoT (Internet of Things) systems, this paper presents an efficient joint parameter estimation and soft nonconherent detection scheme. During the parameter estimation, a joint delay and Doppler shift estimation method is proposed, which is called the JDDSE method. Different from the existing estimation methods, the proposed method utilizes the time-domain characteristic of the LoRa signal and only needs to estimate a joint offset of the delay and Doppler shift instead of their respective offsets. Then, a soft noncoherent detection is developed from the existing work in order to match the JDDSE method. Simulation results indicate the validity of the proposed method under the uplink IoT transmission.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Angle Bidirectional Interaction Model for Entity Linking

SSRN

引用

SSRN 2022年

作者： Hui, Bei Zhang, Lizong Nian, Yuhui Yan, Ke Chen, Jia School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

Entity linking is the task of linking the mention in the text to the corresponding entity in the knowledge graph. It is the way to achieve entity disambiguation which can be used in information retrieval, question and answering, content analysis, knowledge base population. Entity link models learn local compatibility through contents and learn global interdependence through correlation knowledge graph for disambiguation. However, the local compatibility component is usually implemented with a traditional unidirectional attention mechanism, ignoring the interaction between mention and candidate entity in multiple angles. Therefore, we propose the BI-INTEL model, which comprehensively considers the bidirectional interaction between the input document and the knowledge graph from multiple perspectives. In the local compatibility component, we both consider the relevance between mention and candidate entities and the relevance of mention context and description of candidate entity, obtaining the relevance of local information from two perspectives. In the global interdependence component, our stacked random walk layers learn the global interdependence of the candidate entity to enhance the accuracy of entity links. Experiments show that our proposed method has significant improvement compared with current state-of-the-art methods in entity link benchmarks such as AQUAINT, ACE2004, WNEDCWEB (CWEB), etc . © 2022, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Overview Paper A Comprehensive Survey of Digital Image Steganography and Steganalysis

引用

APSIPA Transactions on Signal and Information Processing 2024年第1期13卷

作者： Luo, Weiqi Wei, Kangkang Li, Qiushi Ye, Miaoxin Tan, Shunquan Tang, Weixuan Huang, Jiwu School of Computer Science and Engineering Sun Yat-sen University China School of Software Nanchang University China Shenzhen Key Laboratory of Media Security Shenzhen University China Institute of Artificial Intelligence Guangzhou University China Guangdong Laboratory of Machine Perception and Intelligent Computing Faculty of Engineering Shenzhen MSU-BIT University China

In the realm of digital communications, steganography and steganalysis have become a solution for securely exchanging covert information. This survey initiates with an exploration of the widely used passive-warden scenario model, analyzing its significance, key performance indicators, relevant databases, and clarifying some commonly misunderstood fundamental concepts associated with this model. Subsequently, the paper comprehensively examines the evolution and current state of digital image steganography and steganalysis, highlighting the transition from traditional handcrafted based methods to sophisticated deep learning based techniques developed over the past two decades. It offers thorough descriptions and evaluations of typical methods in both steganography and steganalysis, with a particular emphasis on deep learning-based techniques that have emerged in recent years. Furthermore, the survey identifies significant challenges currently faced in translating theoretical research into practical applications. By integrating these insights, the survey not only charts the historical development and technological advancements in steganography and steganalysis but also establishes a proactive agenda for future research aimed at enhancing security in covert communications. © 2024 W. Luo, K. Wei, Q. Li, M. Ye, S. Tan, W. Tang and J. Huang.

关键词： Steganalysis steganography

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：