检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Zhu, Erzhou Chang, Jiaqi Luo, Siyuan Ma, Zhujuan School of Computer Science and Technology Anhui University Hefei230601 China School of Big Data and Artificial Intelligence Anhui Xinhua University Hefei230088 China

With the increasing availability of computational power, deep learning methods have been widely used for detecting software vulnerabilities in recent years. In contrast to traditional machine learning technology, deep learning methods have the merits of low computational overhead and high vulnerability detection accuracy, and they do not depend on expert knowledge to extract vulnerability features. However, the performance of many existing deep vulnerability detection methods is degraded by inadequate information about the syntax and semantics of source code. This paper proposes Vulnerability Detection based on Deep learning and Attention mechanisms (VDDA), an effective software vulnerability detection model based on deep learning and an attention mechanism. In VDDA, the bidirectional long short-term memory (BLSTM) deep model is used to alleviate the need for the feature engineering of traditional machine learning techniques. With the Joern analysis tool, the source code is converted to code property graphs (CPG) to retain the affluent syntax and semantic information. Several improvements, including depth-first traversal-based CPG optimization, three-direction code slicing, slice organization with code blocks, and the separation of function names from variable names in code symbolization, were made to effectively convert source code into vectors that could be taken as the only input to the underlying deep learning model. Meanwhile, because different parts of the vector play different roles in vulnerability detection, the attention mechanism was integrated with BLSTM to further improve vulnerability detection performance. The experimental results on two datasets of different scales demonstrated that the proposed VDDA outperforms many existing methods in vulnerability detection. © 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

Advancing Oncology Outcomes: Deploying Advanced Machine Learning Models for Early Detection and Optimized Treatment

Advancing Oncology Outcomes: Deploying Advanced Machine Lear...

引用

2024 International Conference on artificial intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Khobragade, Prashant Dhankar, Praveen Kumar Motghare, Manish Golghate, Ashish Rakesh, Nitin Turkar, Hemantkumar Computer Science and Engineering G H Raisoni College of Engineering Nagpur India Pune India G H Raisoni College of Engineering and Management Dept of Artificial Intelligence Nagpur India Nagpur India S.B.Jain Institute of Technology Management and Research Department of Data Science Nagpur India

ISBN: (纸本)9798331517953

The field of oncology is changing quickly as more advanced machine learning (ML) models are added to help find cancer earlier and improve treatment results. This paper looks at how machine learning could change oncology by focusing on how it can be used to find cancer early, predict how it will progress, and create personalized treatment plans. Early identification is very important for increasing the number of people who survive, but standard testing methods aren't always accurate or quick enough. Machine learning calculations can discover patterns and exceptions that conventional investigations might miss by utilizing enormous datasets from an assortment of sources, such as electronic wellbeing records, hereditary information, and imaging thinks about. We see at cutting-edge machine learning models, like deep learning neural systems, support vector machines, and gathering strategies, to see how well they work at finding diverse sorts of cancer prior. The paper discuss about some important examples of how these models have done much better than standard diagnostic tools, allowing for earlier treatments and better patient results. The study emphasize about how natural language processing (NLP) can be used to get useful information from unorganized clinical notes. This can help with diagnosis and give us a fuller picture of the patient's background and risk factors. The study also talks about how predictive models can be used to make treatment plans better. Machine learning models can help doctors adjust treatments to each patient's unique profile by looking at patient data and how they respond to treatment. This makes treatments more effective while reducing side effects. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Sentimental Insight 2.0: Exploring the Frontiers of Opinion Mining with Deep Learning 2

Sentimental Insight 2.0: Exploring the Frontiers of Opinion ...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Murugan, S.Karthick Jayachandran, S. Mageshwari, G. Latha, J. Naveen, G. R. M. D. Engineering College Kavaraipettai Department of Computer Science and Engineering Tamilnadu Thiruvallur India Srm Institute of Science and Technology Department of Computer Science and Application Chennai Ramapuram India R.M.K. College of Engineering and Technology Department of Artificial Intelligence and Data Science Tamilnadu Tiruvallur India R. M. K. Engineering College Department of Computer Science and Engineering Tiruvallur Tamilnadu Kavaraipettai India Madha Institute of Engineering and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350382952

'Sentimental Insight 2.0' emerges as revolutionary research using deep learning techniques in response to the increasing demand for more complex sentiment analysis in the age of information abundance. Traditional sentiment analysis methods sometimes fail to accurately capture the particulars of emotions, sarcasm, and context, demanding a more advanced technique. The existing system's limitations include its inability to detect minor sentiment variations and its vulnerability to noisy and distorted data. The proposed system integrates cutting-edge deep learning architectures such as recurrent neural networks (RNNs), extended short-term memory networks (LSTMs), and transformer models into an extensive structure. The result showcases the advanced sentiment analysis, outperforming existing systems with 94% accuracy, 93% precision, 91% recall, and 93% F1 score, demonstrating superior computational efficiency and emotion classification across diverse sentiments. In the information-centric world, the study's results significantly expand sentiment analysis skills, providing a vital resource for applications in social media analytics, consumer feedback, and market sentiment prediction. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Lightweight and Efficient Motor Imagery Decoding for High-ITR Multi-task Brain-computer Interface 24

Lightweight and Efficient Motor Imagery Decoding for High-IT...

引用

Proceedings of the 2024 10th International Conference on Communication and Information Processing

作者： Xuechen Ma Sifeng Wang Xin Xu Penghui Li Pinyuan Hu Tianhao Liu Suyu Zhong School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing Beijing China School of Computer Science and Technology Shandong Jianzhu University Jinan Shandong China

ISBN: (纸本)9798400717444

Brain-computer Interface (BCI), a technology that enables the direct communication and control between the brain and external devices, have gained significant attention for their potential in various applications, many of which require real-time or online systems. While sufficient hardware performance is essential, optimizing the system's responsiveness largely hinges on minimizing the time window of input data used for analysis. In this paper, we propose a novel method, Time Windows and Frequency bands-Based Convolutional Neural Network (TWFB-CNN), designed to classify motor imagery tasks with a high degree of accuracy using only a 1-second time window. To validate the effectiveness of the proposed method, we conducted experiments using the Neuroscan system to collect electroencephalographic (EEG) data from 20 healthy subjects, each performing seven distinct motor imagery tasks. This dataset, combined with the TWFB-CNN algorithm, is aimed at advancing the state of brain-computer interfaces (BCIs) by enhancing both the classification accuracy and the feasibility of implementing real-time BCIs in practical applications. The results and framework presented here provide a robust foundation for future developments in online BCI systems, particularly in contexts that demand both rapid processing and high precision.

关键词： Brain-computer Interface (BCI)

来源：评论

学校读者我要写书评

暂无评论

The Generated-bbox Guided Interactive Image Segmentation With Vision Transformers

引用

IET computer Vision 2025年第1期19卷

作者： Zhang, Shiyin Dong, Yafei Qiu, Shuang School of Control and Computer Engineering North China Electric Power University Baoding China School of Mathematics and Information Science Hebei University Baoding China School of Artificial Intelligence Taiyuan University of Technology Taiyuan China

Existing click-based interactive image segmentation methods typically initiate object extraction with the first click and iteratively refine the coarse segmentation through subsequent interactions. Unlike box-based methods, click-based approaches mitigate ambiguity when multiple targets are present within a single bounding box, but suffer from a lack of precise location and outline information. Inspired by instance segmentation, the authors propose a Generated-bbox Guided method that provides location and outline information using an automatically generated bounding box, rather than a manually labelled one, minimising the need for extensive user interaction. Building on the success of vision transformers, the authors adopt them as the network architecture to enhance model's performance. A click-based interactive image segmentation network named the Generated-bbox Guided Coarse-to-Fine Network (GCFN) was proposed. GCFN is a two-stage cascade network comprising two sub-networks: Coarsenet and Finenet. A transformer-based Box Detector was introduced to generate an initial bounding box from a inside click, that can provide location and outline information. Additionally, two feature enhancement modules guided by foreground and background information: the Foreground-Background Feature Enhancement Module (FFEM) and the Pixel Enhancement Module (PEM) were designed. The authors evaluate the GCFN method on five popular benchmark datasets and demonstrate the generalisation capability on three medical image datasets. © 2025 The Author(s). IET computer Vision published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and technology.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Attention-Guided Memory Model for Video Object Segmentation 16th

Attention-Guided Memory Model for Video Object Segmentation

引用

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Lin, Yunjian Tan, Yihua National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811912528

Semi-supervised video object segmentation (S-VOS) is defined as pixel-wise separating the object of interest specified to initial mask during inference period. For small object, the exploitable information contained in single frame is limited, making S-VOS task more challenging. Existing methods cannot reach a balance between accuracy and speed on small object sequences. To resolve the problem, we develop an Attention-Guided Memory model (AGM) for video object segmentation by introducing two novel modules, namely Joint Attention Guider (JAG) and spatial-temporal feature fusion (STFF). For accuracy, JAG employs multi-dimension attention mechanism to generate salient feature map, which highlights the object area through visual guide, spatial guide and channel guide. Further, STFF integrates more complete spatial-temporal information by fusing previous memory feature, current high-level salient feature and low-level features, which provides an effective representation of small object. For speed, the STFF employs several light-weight RNNs whose embedded computation architecture is more efficient than the explicit query approach used in the state-of-the-art models. We conduct extensive experiments on DAVIS and YouTube-VOS datasets. For small object on DAVIS 2017, AGM obtains 63.5 % J& F mean with 28.0 fps for 480p, which achieves similar accuracy with about 5x faster speed compared with the state-of-the-art method. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Inter-Language Design Smells in Multi-Language Deep Learning Frameworks

arXiv

引用

arXiv 2024年

作者： Li, Zengyang Zhang, Xiaoyong Wang, Wenshuo Liang, Peng Mo, Ran Tan, Jie Liu, Hui School of Computer Science Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal University Wuhan China School of Computer Science Wuhan University Wuhan China Intelligent Game and Decision Lab Beijing China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Context: Nowadays, most deep learning frameworks (DLFs) use multilingual programming of Python and C/C++, facilitating the flexibility and performance of the DLF. However, inappropriate interlanguage interaction may introduce design smells involving multiple programming languages (PLs), i.e., Inter-Language Design Smells (ILDS). Despite the negative impact of ILDS on multi-language DLFs, there is a lack of an automated approach for detecting ILDS in multi-language DLFs and a comprehensive understanding on ILDS in such DLFs. Objective: This work aims to automatically detect ILDS in multi-language DLFs written in the combination of Python and C/C++, and to obtain a comprehensive understanding on such ILDS in DLFs. Methods: We first developed an approach to automatically detecting ILDS in the multi-language DLFs written in the combination of Python and C/C++, including a number of ILDS and their detection rules defined based on inter-language communication mechanisms and code analysis. Then, we developed the CPSMELL tool that implements detection rules for automatically detecting such ILDS, and manually validated the accuracy of the tool. Finally, we performed an empirical study to evaluate the ILDS in multi-language DLFs. Results: We proposed seven ILDS and achieved an accuracy of 98.17% in the manual validation of CPSMELL in 5 popular multi-language DLFs. The study results revealed that among the 5 DLFs, TensorFlow, PyTorch, and PaddlePaddle exhibit relatively high prevalence of ILDS;each smelly file contains around 5 ILDS instances on average, with ILDS Long Lambda Function For Inter-language Binding and Unused Native Entity being relatively prominent;throughout the evolution process of the 5 DLFs, some ILDS were resolved to a certain extent, but the overall count of ILDS instances shows an upward trend. Conclusions: The automated detection of the proposed ILDS achieved a high accuracy, and the empirical study provides a comprehensive understanding on ILDS in the mu

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Partial Label Learning

Fine-Grained Partial Label Learning

引用

artificial intelligence (CAI), IEEE Conference on

作者： Cheng Chen Yueming Lyu Xingrui Yu Jing Li Ivor W Tsang The Australian Artificial Intelligence Institute (AAII) University of Technology Sydney Australia CFAR Agency for Science Technology and Research Singapore IHPC Agency for Science Technology and Research Singapore School of Computer Science and Engineering College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798350354096

ISBN: (纸本)9798350354102

Partial Label Learning (PLL) involves associating each instance with a candidate label set, which includes the true label along with false positive labels. Traditional PLL approaches typically assume that these false positive labels follow either a uniform or a non-uniform structure, based on the true label of an instance. However, these assumptions do not fully encompass all aspects of real-world scenarios, especially in cases of finegrained objects with subtle differences in appearance. Therefore, we introduce a fine-grained PLL task specifically designed to handle candidate sets that comprise the true label, partially nonuniform fine-grained labels manifesting in a hierarchical structure, and other false positive labels. Nevertheless, the incorporation of these partially non-uniform, fine-grained labels can result in an intractable posterior, leading to an inconsistent classifier. To address this issue, we propose a Specific Classes-Hierarchical (SCH) regularisation that ensures classifier consistency. Subsequently, the Global Label-Hierarchical-wise Embedding (GLHE) regularisation is introduced, using the refined pseudo labels of positive samples from the obtained consistent classifier. This allows the model to learn more distinctive representations from finegrained instances. Our extensive experiments on datasets such as CIFAR-10, CIFAR-100, and CUB-200 have demonstrated the effectiveness of our approach.

关键词： Complexity theory Phase locked loops Task analysis artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Inlier Confidence Calibration for Point Cloud Registration

Inlier Confidence Calibration for Point Cloud Registration

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yongzhe Yuan Yue Wu Xiaolong Fan Maoguo Gong Qiguang Miao Wenping Ma MoE Key Lab of Collaborative Intelligence Systems Xidian University School of Computer Science and Technology Xidian University School of Electronic Engineering Xidian University School of Artificial Intelligence Xidian University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Inliers estimation constitutes a pivotal step in partially overlapping point cloud registration. Existing methods broadly obey coordinate-based scheme, where inlier con-fidence is scored through simply capturing coordinate differences in the context. However, this scheme results in massive inlier misinterpretation readily, consequently affecting the registration performance. In this paper, we explore to extend a new definition called inlier confidence calibration (ICC) to alleviate the above issues. Firstly, we provide finely initial correspondences for ICC in order to generate high quality reference point cloud copy corresponding to the source point cloud. In particular, we develop a soft assignment matrix optimization theorem that offers faster speed and greater precision compared to Sinkhorn. Benefiting from the high quality reference copy, we argue the neighborhood patch formed by inlier and its neighborhood should have consistency between source point cloud and its reference copy. Based on this insight, we construct transformation-invariant geometric constraints and capture geometric structure consistency to calibrate inlier confidence for estimated correspondences between source point cloud and its reference copy. Finally, transformation is further calculated by the weighted SVD algorithm with the calibrated inlier confidence. Our model is trained in an unsupervised manner, and extensive experiments on synthetic and real-world datasets illustrate the effectiveness of the proposed method.

关键词： Point cloud compression computer vision Accuracy Estimation Calibration Pattern recognition Optimization

来源：评论

学校读者我要写书评

暂无评论

A Solution to CVPR'2023 AQTC Challenge: Video Alignment for Multi-Step Inference

arXiv

引用

arXiv 2023年

作者： Zhang, Chao Wu, Shiwei Zhao, Sirui Xu, Tong Chen, Enhong School of Computer Science and Technology University of Science and Technology of China China School of Data Science University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China

Affordance-centric Question-driven Task Completion (AQTC) for Egocentric Assistant introduces a groundbreaking scenario. In this scenario, through learning instructional videos, AI assistants provide users with step-by-step guidance on operating devices. In this paper, we present a solution for enhancing video alignment to improve multi-step inference. Specifically, we first utilize VideoCLIP to generate video-script alignment features. Afterwards, we ground the question-relevant content in instructional videos. Then, we reweight the multimodal context to emphasize prominent features. Finally, we adopt GRU to conduct multi-step inference. Through comprehensive experiments, we demonstrate the effectiveness and superiority of our method, which secured the 2nd place in CVPR’2023 AQTC challenge. Our code is available at https://***/zcfinal/LOVEU-CVPR23-AQTC. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

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：