检索结果-内蒙古大学图书馆

Code detection for Hardware Acceleration Using Large Language Models

IEEE ACCESS 2024年 12卷 35271-35281页

作者： Martinez, Pablo Antonio Bernabe, Gregorio Garcia, Jose Manuel Huawei Technol Res & Dev Cambridge CB4 0WN England Univ Murcia Comp Engn Dept Murcia 30100 Spain

Large language models (LLMs) have been massively applied to many tasks, often surpassing state-of-the-art approaches. While their effectiveness in code generation has been extensively studied (e.g., AlphaCode), their potential for code detection remains unexplored. This work presents the first analysis of code detection using LLMs. Our study examines essential kernels, including matrix multiplication, convolution, fast-fourier transform and LU factorization, implemented in C/C++. We propose both a preliminary, naive prompt and a novel prompting strategy for code detection. Results reveal that conventional prompting achieves great precision but poor accuracy (67.5%, 22.5%, 79.5% and 64% for GEMM, convolution, FFT and LU factorization, respectively) due to a high number of false positives. Our novel prompting strategy substantially reduces false positives, resulting in excellent overall accuracy (91.2%, 98%, 99.7% and 99.7%, respectively). These results pose a considerable challenge to existing state-of-the-art code detection methods.

关键词： Codes Task analysis Computational modeling Convolution Kernel Hardware acceleration Transforms detection algorithms Program processors Large language models Code detection compilers heterogeneous computing high-performance computing large language model

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Multi-User detection for PD-SCMA

引用

IEEE ACCESS 2024年 12卷 75136-75145页

作者： Chege, Simon Walingo, Tom Univ KwaZulu Natal Discipline Elect Elect & Comp Engn ZA-4000 Durban South Africa

The performance of hybrid multi-radio access technologies depends on the sufficiency of the multi-user detection (MUD) at the receiver. For optimal performance of the hybrid power-domain sparse code multiple access (PD-SCMA), robust detection strategies are necessary to alleviate MUD complexity and reduces computational time. Deep learning (DL) based MUD techniques are the most promising as they can detect all symbols of an overloaded PD-SCMA without requiring additional operations of channel estimation and interference cancellation. This work proposes a deep neural network (DNN) aided MUD scheme (DNN-MUD) for an uplink PD-SCMA system supporting near users (NUs) and far users (FUs) multiplexed in power-, and code-domain, respectively. The proposed DNN-MUD features a unified framework that jointly performs successive interference cancellation (SIC) and message passing algorithm (MPA)/expectation propagation algorithm (EPA) operations to overcome interference propagation of SIC and computational complexity of MPA/EPA. The DNN training is enhanced by batch normalization to reduce the internal covariant shifts, thus enhancing the efficiency of detection. Performance results show that the average symbol error rate (SER), complexity and computational time of the proposed DNN-MUD significantly outperforms the conventional joint SIC-MPA/EPA schemes.

关键词： Interference cancellation NOMA Multiuser detection Artificial neural networks Receivers Decoding Symbols Deep learning detection algorithms PD-SCMA deep learning multi-user detection batch normalization SER

来源：评论

学校读者我要写书评

暂无评论

A Parking detection Algorithm Based on Multitransitory Finite-State Machine Using Magnetic Wireless Sensor Network

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第5期11卷 8360-8372页

作者： Zhang, Ying Wu, Chang Liu, Siyan Lv, Zejie Huang, Xiaoman Wu, Peng Univ Elect Sci & Technol China Inst Informat & Commun Engn Chengdu 611731 Peoples R China

Due to the advantages of low-cost, easy use, and high-sensitivity, magnetic sensors are being widely used in parking detection. However, the magnetic signals contain a lot of noise, which can affect the detection performance. In this article, a parking detection algorithm based on a magnetic wireless sensor network is proposed, which adopts the translation-invariant wavelet denoising method to preprocess magnetic signals, aiming to reduce the impact of noise and meet the detection requirements. Considering the problems of weak magnetic vehicles and adjacent vehicle interference in practical applications, a multitransitory finite state machine based on variance signal is designed for parking detection. The experimental results in a standard parking lot show that the proposed algorithm has a significant improvement in accuracy compared with the classical algorithms, and provides theoretical support for building smart parking systems and improving vehicle management efficiency. In addition, the proposed algorithm can also accurately detect the special case of weak magnetic vehicles and has a wider range of applicability.

关键词： detection algorithms Perpendicular magnetic anisotropy Magnetic anisotropy Noise reduction Magnetic sensors Interference Magnetic analysis Finite state machine magnetic sensor parking detection wavelet denoising wireless sensor network

来源：评论

学校读者我要写书评

暂无评论

LSADEN: Local Spatial-Aware Community detection in Evolving Geo-Social Networks

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第7期36卷 3265-3280页

作者： Ni, Li Li, Qiuyu Zhang, Yiwen Luo, Wenjian Sheng, Victor S. Anhui Univ Sch Comp Sci & Technol Hefei 230601 Anhui Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen 518055 Peoples R China Texas Tech Univ Dept Comp Sci Lubbock TX 79409 USA

The identification of the local community structure in geo-social networks has been gaining increasing attention. The structure of geo-social networks evolves over time with the addition/deletion of edges/nodes and the update of node locations, which has motivated recent studies to mine local communities in dynamic geo-social networks. Mining communities in evolving geo-social networks is essential for understanding the evolution of group behaviors. However, in most previous studies on the community mining in dynamic networks, local spatial-aware communities were not identified in evolving geo-social networks. Therefore, in this study, the problem of determining local spatial-aware communities in evolving geo-social networks is proposed. To address this problem, we propose a parameter-free algorithm, called LSADEN. Specifically, LSADEN involves two main steps: i) selecting candidate nodes, where LSADEN defines the community dominance relation under dynamic environments to obtain candidate nodes that improve the community in terms of the community quality or the smoothness between communities at adjacent time stamps;ii) community expansion, where LSADEN designs the Manhattan distance of communities to add some candidate nodes to the local community. Experimental results on six real-world datasets and one synthetic dataset show that LSADEN performs well both in terms of the quality of communities and the smoothness between communities at adjacent time stamps.

关键词： Heuristic algorithms Social networking (online) detection algorithms Nickel Linear programming Synthetic data Search problems Community detection dominance relation evolving geo-social networks local spatial-aware community

来源：评论

学校读者我要写书评

暂无评论

Nighttime Vehicle detection Algorithm Based on Improved Faster-RCNN

引用

IEEE ACCESS 2024年 12卷 19299-19306页

作者： Xu, Yaqing Chu, Kaibin Zhang, Ji Changzhou Univ Sch Comp & Artificial Intelligence Changzhou 213164 Jiangsu Provinc Peoples R China Changzhou Univ Sch Microelect & Control Changzhou 213164 Jiangsu Provinc Peoples R China

Vehicle detection is important for the development of Intelligent Transportation Systems (ITS), which has made great strides in recent years. However, at night, vehicle detection faces many difficulties such as low illumination, street lights, and the appearances vehicle headlights, etc. In order to solve these problems, we propose an improved nighttime vehicle detection algorithm based on Faster R-CNN. Firstly, we combine the Deformable Convolutional Network with Faster R-CNN to improve the detection accuracy features of night vehicles of different sizes and shapes. Secondly, to improve the prediction accuracy of bounding box position information, we adopt Side-Aware Boundary Localization to replace the traditional bounding box prediction. It can further obtain more accurate position information. At the same time, aiming at the imbalance of samples in the training process, we use Oline Hard Example Mining(OHEM) to train samples with a high probability of error to improve the learning effect of a few classes;and to improve the accuracy of night vehicle detection. In addition, we use Soft Non-Maximum Suppression(Soft-NMS) to reduce the number of missed vehicles. The improved algorithm efficiently improves the night vehicle detection accuracy and reduces the model complexity. Furthermore, we verify the effectiveness of each innovation module through ablation experiments and comparison experiments. Finally, the advantages of the improved model in terms of nighttime vehicle detection accuracy are verified by experimenting on the open-source intelligent traffic dataset UA-DETRAC and the open-source diverse automated driving dataset BDD100K.

关键词： Feature extraction Vehicle detection Training Adaptation models Mathematical models Convolution detection algorithms Convolutional neural networks Intelligent transportation systems Nighttime vehicle detection faster R-CNN deformable convolutional network (DCNN) side-aware boundary localization (SABL) intelligent transportation system (ITS)

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Opinion Spam detection: A Systematic Literature Review

引用

IEEE ACCESS 2024年 12卷 143485-143499页

作者： Qazi, Atika Hasan, Najmul Mao, Rui Elhag Mohamed Abo, Mohamed Kumar Dey, Samrat Hardaker, Glenn Univ Brunei Darussalam Ctr Lifelong Learning Bandar Seri Begawan BE1410 Brunei BRAC Univ BRAC Business Sch Dhaka 1212 Bangladesh Nanyang Technol Univ Coll Comp & Data Sci Singapore 6397984 Singapore Future Univ Fac Comp Sci Khartoum 10553 Sudan Bangladesh Open Univ BOU Sch Sci & Technol SST Gazipur 1705 Bangladesh King Abdullah Univ Sci & Technol Off Provost Thuwal 23955 Saudi Arabia

The substantial upsurge in Web 2.0 deployment allows a large number of consumers to share their opinions with potential consumers and producers through product and service review platforms. Customer decision-making relies on an important aspect of review: spam-free opinions. Unfortunately, fraudulent activities produced spam reviews that misled potential buyers and traders. Subsequently, it does stop opinion-mining techniques from reaching accurate conclusions. This study aims to identify and review existing state-of-the-art methodologies for three groups: 1) spam reviews;2) individual spammers;and 3) group spam. The machine learning (ML) and deep learning (DL) techniques for spam detection are categorized, and we establish an assessment that may be deemed appropriate in the field. The findings reveal a total of 10 metrics, with accuracy being the most often used (25%) concerning ML-based techniques in spam detection. Followed by recall in 24% of studies, and precision in 22% of studies. In addition, the F-measure, the area under the curve (AUC), and F1-score evaluation metrics reveal that the use of the Amazon dataset as a whole increased by 7%. This study concludes that the majority of SMS spam filtering strategies are leading solutions. In addition, the taxonomy of existing state-of-the-art methodologies is developed, and it is concluded that a substantial number of studies utilize these existing SMS anti-spam applications. This research uncovered previously unexplored areas of ML and DL's application to spam review and provided a new paradigm for applying these technologies to the issue. The findings provide both academics and practitioners with a deeper understanding of the barriers to spam review identification, as well as potential improvement opportunities using ML techniques. These individuals will now have the chance to consider a benchmark for future research.

关键词： Reviews Business Sentiment analysis Decision making Unsolicited e-mail Systematics Object recognition detection algorithms Group spam machine learning opinion mining opinion spam detection spammer detection sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Novel Voting Model Based on Parity Check Equations for Blind detection of M-Sequences

引用

IEEE ACCESS 2024年 12卷 34131-34140页

作者： Wang, Ping Yang, Qiang Hu, Yangheng Xiong, Jian Jia, Yong Guo, Dequan Chengdu Technol Univ Sch Network & Commun Engn Chengdu 610731 Sichuan Peoples R China Chengdu Univ Informat Technol Sch Automat Chengdu 610225 Sichuan Peoples R China Jiangxi Normal Univ Key Lab Nat Disaster Monitoring & Early Warning & Nanchang 330022 Peoples R China Chengdu Univ Technol Sch Mech & Elect Engn Chengdu 610225 Sichuan Peoples R China

A novel acquisition scheme of pseudo-noise (PN) codes is proposed for spreading satellite communication systems relying on the proposed multi-voter model of this paper. Based on the proposed model, the acquisition of PN codes can be attributed to a voting and selecting mechanism to pick out the erroneous chips. Although message passing algorithm (MPA) is a feasible algorithm for decoding PN codes, MPA does not get good detection performance due to the limited number of parity check equations in the acquisition scheme. To overcome the negative impact of the limited number of parity check equations, this paper proposes single-voter and multi-voter models, which combine chip and sequence estimation on the basis of the chip-flipping (CF). It is known that the bit-flipping (BF), weighted-bit-flipping (WBF) and other algorithms based on BF are credible for low density parity check (LDPC) codes. Because of the lack of research, these algorithms have not been extended to the detection of PN codes. As the same as BF, the inputs of the proposed CF algorithm are the hard-decision samples. For the proposed CF, there exists an optimal flipping-threshold which is similar to the random weight of the WBF. Owing to the low computation complexity of CF, the unlimited number of parity check equations can be enabled in the voting model. The experimental results show that the detection performance of the proposed method of N > 15 is improved by 2 dB compared with MAP-based method and 4 dB compared with LEAP-based method at the detection probability 99%.

关键词： Mathematical models Correlation Decoding Receivers Iterative decoding Estimation Computational complexity detection algorithms Spread spectrum communication PN codes voting model detection algorithm MPA

来源：评论

学校读者我要写书评

暂无评论

Multi Pattern Features-Based Spoofing detection Mechanism Using One Class Learning

引用

IEEE ACCESS 2024年 12卷 117523-117540页

作者： Ustubioglu, Beste Tahaoglu, Gul Ustubioglu, Arda Ulutas, Guzin Amerini, Irene Kilic, Muhammed Karadeniz Tech Univ Comp Engn Dept TR-61080 Trabzon Turkiye Univ Florence Dept Informat Engn I-50139 Florence Italy Trabzon Univ Dept Management Informat Syst TR-61335 Trabzon Turkiye Sapienza Univ Rome Dept Comp Control & Management Engn I-00185 Rome Italy

Automatic Speaker Verification systems are prone to various voice spoofing attacks such as replays, voice conversion (VC) and speech synthesis. Malicious users can perform specific tasks such as controlling the bank account of someone, taking control of a smart home, and similar activities, by using advanced audio manipulation techniques. This study presents a Multi-Pattern Features Based Spoofing detection mechanism using the modified ResNet architecture and OC-Softmax layer to detect various LA and PA spoofing attacks. We proposed a novel Pattern features-based audio spoof detection scheme. The scheme contains three branches to evaluate different patterns on a Mel spectrogram of the audio file. This is the first work for the audio spoofing detection task using three different pattern representations of Mel spectrogram with modified ResNet architecture and OC-Softmax layer. Through the proposed network, we can extract pattern images from the Mel spectrogram and gives each of them into modified ResNet architecture. At the last step of each network, we use OC-Softmax to obtain a score for the current pattern image and then the method fuses three scores to label the input audio. Experimental results on the ASVspoof 2019 and ASVspoof 2021 corpuses show that the proposed method achieves better results in the challenges of ASVspoof 2019 than state-of-the-art methods. For example, in the logical access scenario, our model improves the tandem decision cost function and equal error rate scores by 0.06% and 2.14%, respectively, compared with state-of-the-art methods. Additionally, experiments illustrate that the proposed fused decision improved the performance of the system.

关键词： Feature extraction Transforms Spectrogram Training Cost function Convolutional neural networks Deepfakes Forgery detection algorithms Deep fake audio audio forgery forgery detection

来源：评论

学校读者我要写书评

暂无评论

Quickest Change detection for Unnormalized Statistical Models

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2024年第2期70卷 1220-1232页

作者： Wu, Suya Diao, Enmao Banerjee, Taposh Ding, Jie Tarokh, Vahid Duke Univ Dept Elect & Comp Engn Durham NC 27708 USA Univ Pittsburgh Dept Ind Engn Pittsburgh PA 15213 USA Univ Minnesota Sch Stat Minneapolis MN 55455 USA

Classical quickest change detection algorithms require modeling pre-change and post-change distributions. Such an approach may not be feasible for various machine learning models because of the complexity of computing the explicit distributions. Additionally, these methods may suffer from a lack of robustness to model mismatch and noise. This paper develops a new variant of the classical Cumulative Sum (CUSUM) algorithm for the quickest change detection. This variant is based on Fisher divergence and the Hyvarinen score and is called the Hyvarinen score-based CUSUM (SCUSUM) algorithm. The SCUSUM algorithm allows the applications of change detection for unnormalized statistical models, i.e., models for which the probability density function contains an unknown normalization constant. The asymptotic optimality of the proposed algorithm is investigated by deriving expressions for average detection delay and the mean running time to a false alarm. Numerical results are provided to demonstrate the performance of the proposed algorithm.

关键词： Change detection algorithms Delays Computational modeling detection algorithms Machine learning Random variables Numerical models Quickest change detection CUSUM fisher divergence score matching unnormalized models

来源：评论

学校读者我要写书评

暂无评论

Shared-Memory Parallel algorithms for Community detection in Dynamic Graphs

Shared-Memory Parallel Algorithms for Community Detection in...

引用

IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Subhajit Sahu Kishore Kothapalli Dip Sankar Banerjee International Institute of Information Technology Hyderabad India Hyderabad India Indian Institute of Technology Jodhpur India Karwar Rajasthan India

ISBN: (数字)9798350364606

ISBN: (纸本)9798350364613

Community detection is the problem of identifying natural divisions in networks. A relevant challenge in this problem is to find communities on rapidly evolving graphs. In this paper, we present our parallel Dynamic Frontier (DF) approach. Given a batch update of edge deletions or insertions, this approach incrementally identifies an approximate set of affected vertices in the graph with minimal overhead. We apply this approach to both Louvain, a high quality, and Label Propagation Algorithm (LPA), a fast static community detection algorithm. Our approach achieves a mean speedup of 7.3 × and 6.7 ×, when applied to Louvain and LPA respectively, compared to our parallel and optimized implementation of Δ-screening, a recently proposed state-of-the-art approach. Finally, we show how to combine Louvain and LPA with the DF approach to arrive at a hybrid algorithm. This algorithm produces high-quality communities while providing a speedup of 2.0 x on top of DF -based Louvain.

关键词： Distributed processing Heuristic algorithms Image edge detection Conferences Approximation algorithms detection algorithms Parallel algorithms

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：