检索结果-内蒙古大学图书馆

International Conference on Data science and Network engineering, ICDSNE 2023

作者： Prasath, Navamani Jasthi, Monika Saikia, Rabul Loganathan, Muralidaran Devi, Salam Shuleenda Department of Electronics and Communication Engineering NIT Meghalaya Meghalaya Shillong793003 India Department of Computer Science and Information System Engineering St. Joseph University Dae Es Salaam Tanzania United Republic of

ISBN: (纸本)9789819967544

Acute lymphoblastic leukemia (ALL) is a cancerous condition that affects the bone marrow and blood. It is a fast developing illness that, if not identified and treated as soon as possible, could be fatal. ALL is often identified by looking at blood and bone marrow smears under a microscope. Leukemia can be detected and classified using detailed cytochemical tests. However, these procedures are expensive, time-consuming, and dependent on the knowledge and skills of the specialists involved. Using image processing techniques that examine microscopic blood smear images to search for the leukemic cells, leukemia can be detected. These methods are simple, quick, cost-effective, and unaffected by the judgments of experts. The suggested study describes a computer-aided diagnosis method that uses deep convolutional neural networks (CNNs) that have already been trained to compare leukemia images to normal images. The public dataset ALL-IDB 2 was used for the proposed research. The study uses the pre-trained model DenseNet-201 for performing the classification. With the DenseNet201 pre-trained networks employed in the study for the ALL_IDB2 dataset, a classification accuracy of 94.6% is achieved. In all of the classifications carried out, optimization strategies such as cross-validation, fine-tuning, and real-time augmentation are also compared. Also use Pre-trained series models like ResNet-50, VGG-19, Inceptionv3, MobileNet-v2, Xceptionv3, and VGG-16 for performing the comparison. The experimental result gives an improvement in accuracy (17.76, 10.6, and 13.2%) in comparison to the other approaches namely, residual neural network, customized combined CNN, and conVNet neural network, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Defect Screening on Nuclear Power Plant Concrete Structures: A Two-staged Method Based on Contrastive Representation Learning 8

Defect Screening on Nuclear Power Plant Concrete Structures:...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Huang, Wenlian Zhu, Guanming Huang, Qiang Chen, Zhuangzhuang Chen, Jie Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China

ISBN: (纸本)9798350300178

Intelligent defect detection methods are important for the surface of the containment of nuclear power plants and face many challenges in the field of computer vision. Due to the irregular shapes and large variation of defects, as well as the similarity of the features between some defects and the background. Most existing deep learning-based defect detection networks suffer from insufficient feature extraction capabilities, making it difficult to detect defects from the background. Inspired by discrete representation learning methods, we propose a two-stage defect detection model called ConVQVAE, which uses a semi-supervised method for representation learning to achieve binary classification for defect detection. In addition, contrastive learning is performed in two stages to enhance the model's diversity representation ability and inter-class disentanglement representation ability. Finally, we experimentally verify that the proposed method can obtain good classification results. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities 24

On the Effectiveness of Function-Level Vulnerability Detecto...

引用

44th ACM/IEEE International Conference on Software engineering, ICSE 2024

作者： Li, Zhen Wang, Ning Zou, Deqing Li, Yating Zhang, Ruqian Xu, Shouhuai Zhang, Chao Jin, Hai Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hong Kong Jin YinHu Laboratory Wuhan China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China University of Colorado Colorado Springs Department of Computer Science Colorado Springs Colorado United States Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798400702174

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter -Procedural Vulnerability Dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers;and (ii) function-level vulner-ability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities. © 2024 ACM.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning 27

Video2Reward: Generating Reward Function from Videos for Leg...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781643685489

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. © 2024 The Authors.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Smart Material Selection: Leveraging Machine Learning for Sustainable and Cost-Effective Building Design 2

Smart Material Selection: Leveraging Machine Learning for Su...

引用

2nd Jordanian International Biomedical engineering Conference, JIBEC 2024

作者： Hashim, Wassan Adnan Khoshaba, Lina Sami Kareem, Shahab Wahhab Khoshaba, Farah Sami Al-Qalam University College Medical Device Engineering Department Kirkuk Iraq Lebanese French University College of Engineering and Computer Science Architecture Engineering Department Erbil Iraq Polytechnic University Technical Engineering College Information System Engineering Department Erbil Iraq

ISBN: (纸本)9798331539542

In modern-day architecture, the choice of building material plays an important role in sustainability, cost-value engineering, and design integrity. Moreover, the traditional methods for selecting materials tended to make use of manual approaches, which at times led to drawbacks by not focusing on the basics of integration and proper data management. The paper is a very interesting approach of how a complex material selection process can be optimized with simple machine learning algorithms. In that sense, the current research developed a framework from environmental sustainability to economic cost, durability, and aesthetic appeal, with an intention for its use in guiding the design final decision process. The proposed machine learning model suggests ideal prediction for material combination from different material datasets concerning the properties and performance metrics applicable to architecture. The research showed that the approach had a hand in getting thoughtful, analytic-based decisions while assuring, at the same time, that an architect would be able to satisfy the project goals and budget constraints with environmentally safe execution. It elaborates on the cases, or rather case studies, that have applied the model and gives illustrations of great improvements not only in efficiency in design but also in the sustainability of the project coupled with better strategies for saving costs. The current research is opening an entirely new field of innovation in architecture that emphasizes the role of technology for the future form of building practice. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

A lightweight point cloud analysis network based on graph walking 8

A lightweight point cloud analysis network based on graph wa...

引用

8th International Conference on Intelligent Informatics and Biomedical sciences, ICIIBMS 2023

作者： Li, Wenju Ji, Qianqian Sha, Liye Cui, Liu Shanghai Institute of Technology School of Computer Science and Information Engineering Shanghai China Shanghai Precision Dosing & Weighing System Co Shanghai China

ISBN: (纸本)9798350369564

Based on the irregularity and permutation invariance of point clouds, graph neural networks have been widely used in 3D point cloud analysis tasks in recent years. However, these works suffer from insufficient feature extraction at long distances and high computational resource overhead. To this end, this paper proposes a graph walk based lightweight network for 3D point cloud analysis tasks. Specifically, after constructing the nearest neighbor graph in the downsampled point cloud, the MLP module in the original network was replaced by multiple nonparametric components to reduce the number of parameters of the model. Then, the graph walking mechanism was used to extract the long-distance features and geometric structure features of the point cloud. Finally, before point classification and segmentation, the residual pooling module is used to fuse the features to obtain the global features. Compared with the benchmark network DGCNN, the classification accuracy on the ScanObjectNN dataset is improved by 4.2%, the segmentation accuracy on the ShapeNetPart dataset is improved by 1.1%, and the number of model parameters is reduced by 33.3%. Experiments show that the design method has obvious effect on 3D point cloud analysis tasks. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Integrated operating room planning and scheduling: an ILP-Based off-line approach for emergency responsiveness at a local hospital in Naples

引用

Soft Computing 2024年第20期28卷 11987-12003页

作者： Boccia, Maurizio Mancuso, Andrea Masone, Adriano Sterle, Claudio Department of Electrical Engineering and Information Technology University of Naples "Federico II" Via Claudio 21 Naples80125 Italy Institute for System Analysis and Computer Science "Antonio Ruberti" National Research Council of Italy via dei Taurini 19 Rome00185 Italy

This paper addresses a real-world Integrated Operating Room Planning and Scheduling (IORPS) problem encountered by a local hospital in Naples, characterized by stringent emergency management constraints, requiring treatment initiation within a 20-minute time-window. We tackle this problem by an original Integer Linear Programming formulation, capable of dealing with different operating room management strategies (open, block and block-modified). Our work differs from conventional cost-focused models by adopting a patient-oriented objective function, aligning with public hospitals obligations. The proposed method has been validated using real-world data provided by the hospital. The performed experimentation demonstrates the efficiency of the approach, capable of determining the optimal solution within an acceptable computation time that aligns with hospital requirements. Moreover, it also highlights the relevance of using our optimization approach to reduce delays in emergency responsiveness. This confirms its practical usage as a substitute for the current manual procedure. © The Author(s) 2024.

关键词： Operating rooms

来源：评论

学校读者我要写书评

暂无评论

A motion-level-aware denoising framework for x-ray fluoroscopic images

A motion-level-aware denoising framework for x-ray fluorosco...

引用

Medical Imaging 2023: Physics of Medical Imaging

作者： Jo, Geonhui Jang, Minhee Jeon, Sun-Young Kim, Wonjin Choi, Jang-Hwan Department of Computer Science and Engineering Ewha Womans University Seoul03760 Korea Republic of Division of Mechanical and Biomedical Engineering Graduate Program in System Health Science and Engineering Ewha Womans University Seoul03760 Korea Republic of

ISBN: (纸本)9781510660311

Fluoroscopy in a low-dose tube output is used to reduce the damage associated with radiation exposure. However, lowering the radiation dose inevitably increases random noise in x-ray images, resulting in poor diagnostic image quality, which requires noise reduction for accurate diagnosis. Also, in the case of non-static objects, the image is blurred due to motion. The most-used denoiser with a recursive filter (RF) preserves details well when applied to temporal data, but it is vulnerable to motion blur. Existing convolutional neural network (CNN)-based algorithms with single-frame input cannot use the temporary context, and others with multi-frame input are good for motion detection but poor for detail preservation. Therefore, we propose a motion-level-aware denoising framework to combine the results of RF- and CNN-based algorithms depending on the pixel-wise magnitude of motion to complement each other. The data we use are fluoroscopy images taken in continuous time, and we aim at many-to-one so that one frame is denoised by considering sequential frames. Also, since both RF- and CNN-based algorithms used in our architecture are many-to-one methods, they can consider spatiotemporal information. In the multi-frame input, the difference in intensity of each pixel between frames is calculated to obtain a moving map. Depending on the factor value from the moving map, the final image is obtained by reflecting the outputs of the RF- and CNN-based algorithms. If the factor value is high, the pixel intensity of the final image is like the CNN-based output, which is good for motion detection, and vice versa, it more reflects the intensity of RF output, which is excellent in perceptual quality. Therefore, it prevents motion blur and does not over-smooth microdetails, such as bones and muscles. The results show that combining the two outputs together records higher peak signal-to-noise ratio (PSNR) and has better perceptual quality for diagnosis than using only one method. F

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Study of Data Augmentation for Imbalance Problem in Network Traffic 3

A Study of Data Augmentation for Imbalance Problem in Networ...

引用

3rd International Conference on Blockchain Technology and Information Security, ICBCTIS 2023

作者： Wang, Xu Sun, Shimin Han, Li School of Computer Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Autonomous Intelligent Technology and System School of Software Tiangong University Tianjin China School of Computer Science and Engineering Tianjin University of Technology National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin China

ISBN: (纸本)9798350340402

The complexity and diversity of smart grid systems increase the likelihood of anomalies in communications between devices in the system, and how these anomalies are detected is critical to the security of the grid system. However, the distribution of traffic types in the grid is often highly unbalanced, with the total amount of normal traffic data often far outweighing the anomalous data. This imbalance compromises the effectiveness of the detection model and poses a significant threat to the overall security of the grid This paper improves on traditional conditional generation adversarial neural networks and designs a new approach to overcome this obstacle and enhance the security of smart grid systems. In the generator part, the spatial features of the data are captured by convolutional neural networks, and the temporal features of the data are captured by gated recurrent units. By integrating these two components into the generative network we can generate synthetic data with both temporal and spatial features, thus enhancing the minority class samples. By incorporating the augmented minority data into the training process, the proposed approach enables the detection model to understand the distribution of features of the minority anomaly samples more accurately. This improved learning accuracy translates into improved model performance, resulting in higher detection rates for Previously under-represented anomalies. In addition, our approach effectively addresses the inherent bias towards traffic types with higher flows typically observed in asymmetric datasets, thus providing a more equitable and comprehensive security solution for smart grid systems. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Effective and Imperceptible Adversarial Textual Attack Via Multi-objectivization

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第3期4卷 1-23页

作者： Liu, Shengcai Lu, Ning Hong, Wenjing Qian, Chao Tang, Ke Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen College of Engineering South Tower 1088 Xueyuan Avenue Guangdong Shenzhen518055 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong999077 Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen 10F Zhizhen Building Canghai Campus 3688 Nanhai Avenue Guangdong Shenzhen China National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing University Nanjing International College Area Xianlin Campus 163 Xianlin Avenue Jiangsu Nanjing China

The field of adversarial textual attack has significantly grown over the past few years, where the commonly considered objective is to craft adversarial examples (AEs) that can successfully fool the target model. However, the imperceptibility of attacks, which is also essential for practical attackers, is often left out by previous studies. In consequence, the crafted AEs tend to have obvious structural and semantic differences from the original human-written text, making them easily perceptible. In this work, we advocate leveraging multi-objectivization to address such an issue. Specifically, we reformulate the problem of crafting AEs as a multi-objective optimization problem, where the attack imperceptibility is considered as an auxiliary objective. Then, we propose a simple yet effective evolutionary algorithm, dubbed HydraText, to solve this problem. HydraText can be effectively applied to both score-based and decision-based attack settings. Exhaustive experiments involving 44,237 instances demonstrate that HydraText consistently achieves competitive attack success rates and better attack imperceptibility than the recently proposed attack approaches. A human evaluation study also shows that the AEs crafted by HydraText are more indistinguishable from human-written text. Finally, these AEs exhibit good transferability and can bring notable robustness improvement to the target model by adversarial training. © 2024 Copyright held by the owner/author(s).

关键词： Multiobjective optimization

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：