检索结果-内蒙古大学图书馆

Mi-DETR: For Mitosis detection From Breast Histopathology Images an Improved DETR

IEEE ACCESS 2024年 12卷 179235-179251页

作者： Ardac, Fatma Betul Kara Erdogmus, Pakize Duzce Univ Fac Engn Dept Comp Engn TR-81620 Duzce Turkiye

In histopathological image analysis, the detection and count of mitotic cells are important biomarkers for determining the degree and aggressiveness of cancer prognosis. Manual detection of mitosis by pathologists is a lengthy and challenging process. With advancements in deep learning architectures, numerous automatic mitotic detection methods have been proposed. However, most mitotic detection methods lack generalizability across image areas and are not consistently reproducible in multi-center environments. To overcome these issues, a new automatic mitotic detection approach called the Mi-DETR, based on the DETR architecture, has been proposed. In the proposed Mi-DETR model, the backbone of the original DETR is replaced by CSPResNeXt. The aim of this is to strengthen the learning capacity in feature extraction and increase the variability of the learned features. In this way, information loss and unwanted gradient flow are avoided. In the decoder layer, unnecessary model parameters have been filtered out using a layer reduction strategy to improve model efficiency and reduce computational costs. Additionally, a more stable model has been obtained by using the CIoU loss function instead of the L1+GIoU loss function used in the DETR model. The publicly available ICPR14 and TUPAC16 breast histopathology datasets were used for training, validation, and testing in the experiments. The results provided more precise and compact bounding boxes close to clinically validated ground truth, demonstrating the accuracy and generalizability of the proposed model. As a result, the proposed Mi-DETR model achieved a 0.921 F1-score on the ICPR14 dataset and a 0.950 F1-score on the TUPAC16 dataset. The results obtained on both datasets demonstrate that the proposed model performs well enough to compete with state-of-the-art deep learning architectures.

关键词： Feature extraction Transformers Computer architecture Object oriented modeling Computational modeling Histopathology Breast cancer Solid modeling Accuracy Training detection algorithms DETR mitosis detection transformer

来源：评论

学校读者我要写书评

暂无评论

Ship Grid: A Novel Anchor-Free Ship detection Algorithm

引用

IEEE INTELLIGENT SYSTEMS 2024年第5期39卷 47-56页

作者： Chen, Yantong Zhang, Yanyan Wang, Jialiang Liu, Yang Dalian Maritime Univ Dalian 116026 Liaoning Peoples R China

Video-based ship detection is crucial for the real-time monitoring of maritime activities, aiding decision making in maritime traffic management, safety monitoring, and rescue operations. Current challenges include multiscale variations and occlusion issues affecting detection accuracy. Existing ship detection methods often address the multiscale problem by redesigning the network architecture, providing limited improvements. We present Ship Grid, an innovative anchor-free ship detection algorithm. Ship Grid tackles the challenges of ship feature capture in occluded scenarios by directly generating bounding boxes at the predicted centers during the label assignment phase. Moreover, it enables simultaneous ship feature extraction at multiple scales, effectively addressing the issues of insufficient feature extraction for small objects and imprecise localization for large objects caused by stark scale variations. In the bounding box regression phase, we introduce a scale-invariant localization loss that guides the regression process of prediction boxes at different scales. This approach allows the network to comprehensively learn ship features across multiple scales and further enhances performance in the presence of large ship scale variations. We rigorously evaluated the ship grid on the SeaShips dataset, achieving 0.988 and 0.835 on the evaluation metrics of mean average precision (mAP) at an intersection over union (IoU) threshold of 0.5 and mAP at IoU thresholds ranging from 0.5 to 0.95 This outperforms state-of-the-art methods, demonstrating its advantage in ship detection.

关键词： Marine vehicles Feature extraction Shape Location awareness Intelligent systems detection algorithms Computer vision

来源：评论

学校读者我要写书评

暂无评论

Research on Fire Smoke detection Algorithm Based on Improved YOLOv8

引用

IEEE ACCESS 2024年 12卷 117354-117362页

作者： Zhang, Tianxin Wang, Fuwei Wang, Weimin Zhao, Qihao Ning, Weijun Wu, Haodong Liaoning Petrochem Univ Sch Artificial Intelligence & Software Fushun 113005 Peoples R China

Fire has consistently posed a significant disaster risk worldwide. Current fire detection methods primarily rely on traditional physical sensors such as light, smoke, and temperature detectors, which often struggle in complex environments. The susceptibility of existing fire detection technologies to background interference frequently results in false alarms, missed detections, and low detection accuracy. To address these issues, this paper proposes a fire detection algorithm based on an improved YOLOv8 model. First, to enhance the detection capabilities for large-scale fire and smoke targets, a large target detection head is added to the backbone of the YOLOv8 model. This modification enhances the network's receptive field, allowing it to capture a broader range of contextual information and identify fires over extensive areas. Secondly, an efficient multi-scale attention mechanism, EMA (Efficient Multi-Scale Attention Module), based on cross-space learning is integrated into the FPN (Feature Pyramid Network) part of the model. This mechanism highlights target features while suppressing background interference. Additionally, a PAN-Bag (Path Aggregation Network Bag) structure is proposed to help the model more accurately detect objects such as fire and smoke, which have uneven feature distributions and variable morphologies. With these improvements, we introduce the YOLOv8-FEP algorithm, which offers higher detection accuracy. Experimental results demonstrate that the YOLOv8-FEP algorithm improves the mAP by 3.1% and the accuracy by 5.8% compared to the original YOLOv8 algorithm, proving the effectiveness of the enhanced algorithm.

关键词： Feature extraction Accuracy YOLO detection algorithms Convolutional neural networks Forestry Attention mechanisms Fire detection YOLOv8 EMA PAN-Bag

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

Code detection for Hardware Acceleration Using Large Language Models

引用

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

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

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

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

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

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：