检索结果-内蒙古大学图书馆

6th Northern Lights Deep Learning Conference, NLDL 2025

作者： Møller, Bjørn Amiri, Sepideh Igel, Christian Wickstrøm, Kristoffer Knutsen Jenssen, Robert Keicher, Matthias Azampour, Mohammad Farid Navab, Nassir Ibragimov, Bulat Department of Computer Science University of Copenhagen Copenhagen Denmark Department of Physics and Technology UiT The Arctic University of Norway Tromsø Norway Norwegian Computing Center Oslo Norway Technical University of Munich Munich Germany

A fundamental barrier to the adoption of AI systems in clinical practice is the insufficient transparency of AI decision-making. The field of Explainable Artificial Intelligence (XAI) seeks to provide human-interpretable explanations for a given AI model. The recently proposed Neural Explanation Mask (NEM) framework is the first XAI method to explain learned representations with high accuracy at real-time speed. NEM transforms a given differentiable model into a self-explaining system by augmenting it with a neural network-based explanation module. This module is trained in an unsupervised manner to output occlusion-based explanations for the original model. However, the current framework does not consider labels associated with the inputs. This makes it unsuitable for many important tasks in the medical domain that require explanations specific to particular output dimensions, such as pathology discovery, disease severity regression, and multi-label data classification. In this work, we address this issue by introducing a loss function for training explanation modules incorporating labels. It steers explanations toward target labels alongside an integrated smoothing operator, which reduces artifacts in the explanation masks. We validate the resulting Neural Explanation Masks with target labels (NEMt) framework on public databases of lung radiographs and skin images. The obtained results are superior to the state-of-the-art XAI methods in terms of explanation relevancy mass, complexity, and sparseness. Moreover, the explanation generation is several hundred times faster, allowing for real-time clinical applications. The code is publicly available at //***/baerminator/NEM T. © NLDL *** rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Testing GPU Numerics: Finding Numerical Differences Between NVIDIA and AMD GPUs

Testing GPU Numerics: Finding Numerical Differences Between ...

引用

2024 Workshops of the International Conference for High Performance computing, Networking, Storage and Analysis, SC Workshops 2024

作者： Zahid, Anwar Hossain Laguna, Ignacio Le, Wei Iowa State University Department of Computer Science AmesIA United States Lawrence Livermore National Laboratory Center for Applied Scientific Computing LivermoreCA United States

ISBN: (纸本)9798350355543

As scientific codes are ported between GPU platforms, continuous testing is required to ensure numerical robustness and identify potential numerical differences between platforms. Compiler-induced numerical differences can occur when a program is compiled and run on different GPUs and compilers, and the numerical outcomes are different for the same input. We present a study of compiler-induced numerical differences between NVIDIA and AMD GPUs, two widely used GPUs in HPC clusters. Our approach uses a random program generator (Varity) to generate thousands of short numerical tests in CUDA and HIP, and their inputs;then, we use differential testing to check if the program produced a numerical inconsistency when run on NVIDIA and AMD GPUs, using the same compiler optimization level. We also use the AMD's HIPIFY tool to convert CUDA tests into HIP tests and test if there are numerical inconsistencies induced by HIPIFY. In our study, we generated more than 600,000 tests and found subtle numerical differences occurring between the two classes of GPUs. We found that some of the differences come from (1) math library calls, (2) differences in floating-point precision (FP64 versus FP32), and (3) converting code to HIP with HIPIFY. © 2024 IEEE.

关键词： CUDA Differential testing floating-point HIP random program generation

来源：评论

学校读者我要写书评

暂无评论

The Impact of Domain Name Server(DNS)over Hypertext Transfer Protocol Secure(HTTPS)on Cyber Security:Limitations,Challenges,and Detection Techniques

引用

computers, Materials & Continua 2024年第9期80卷 4513-4542页

作者： Muhammad Dawood Shanshan Tu Chuangbai Xiao Muhammad Haris Hisham Alasmary Muhammad Waqas Sadaqat Ur Rehman Faculty of Information Technology Beijing University of TechnologyBeijing100124China National Center of Robotics and Automation University of Engineering and TechnologyPeshawar25000Pakistan Department of Computer Science College of Computer ScienceKing Khalid UniversityAbha61421Saudi Arabia School of Computing and Engineering Sciences Faculty of Engineering and ScienceUniversity of GreenwichLondonSE109LSUnited Kingdom School of Engineering Edith Cowan UniversityPerthWA 6027Australia School of Computer Science and Engineering University of SalfordManchesterM54BRUnited Kingdom

The DNS over HTTPS(Hypertext Transfer Protocol Secure)(DoH)is a new technology that encrypts DNS traffic,enhancing the privacy and security of ***,the adoption of DoH is still facing several research challenges,such as ensuring security,compatibility,standardization,performance,privacy,and increasing user *** significantly impacts network security,including better end-user privacy and security,challenges for network security professionals,increasing usage of encrypted malware communication,and difficulty adapting DNS-based security ***,it is important to understand the impact of DoH on network security and develop newprivacy-preserving techniques to allowthe analysis of DoH traffic without compromising user *** paper provides an in-depth analysis of the effects of DoH on *** discuss various techniques for detecting DoH tunneling and identify essential research challenges that need to be addressed in future security ***,this paper highlights the need for continued research and development to ensure the effectiveness of DoH as a tool for improving privacy and security.

关键词： DNS DNS over HTTPS cybersecurity machine learning

来源：评论

学校读者我要写书评

暂无评论

Genre Classification of Bangla Poem Using Machine Learning and Deep Learning Techniques

Genre Classification of Bangla Poem Using Machine Learning a...

引用

2023 IEEE World AI IoT Congress, AIIoT 2023

作者： Pasha, Syed Tangim Islam, Ashraful Rahman, Mohammed Masudur Ahmed, Eshtiak Ahmed Foysal, Md. Ferdouse Zahangir Alam, Md Daffodil International University Department of Computing and Information System Bangladesh Independent University Center for Computational and Data Sciences Bangladesh Independent University Department of Computer Science and Engineering Bangladesh International Standard University Department of Computer Science and Engineering Bangladesh Daffodil International University Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350337617

The computational analysis of the Bangla poems is a challenging task due to the diverse linguistic, stylistic, and semantic features of the Bangla language. In this work, we prepared a dataset of 1311 Bangla poems of two separate categories: Love and Miscellaneous poem, which contain 500 and 811 poems respectively. We used word or semantic-based features to classify Bangla poems using the TF-IDF feature techniques. We used Logistic Regression, Naïve Bayes (NB), and Support Vector Machine (SVM) models for classification through machine learning, and we used Bayesian optimization techniques for hyperparameters tuning of these three models. We also used LSTM, CNN, and transformer models for this research. For the performance evaluation of the classification models, we used four evaluation metrics of precision, recall, F1-score, and accuracy. We also used the ROC-AUC curve to distinguish between all the machine learning and deep learning models. The experimental results expressed that, the transformer model achieved the highest accuracy compared to all the typical machine learning and deep learning models with an accuracy of 87%. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Generalized hybrid LiFi-WiFi UniPHY learning framework towards intelligent UAV-based indoor networks

引用

International Journal of Intelligent Networks 2024年第1期5卷 255-266页

作者： Ahmad, Rizwana Anwar, Dil Nashin Bany Salameh, Haythem Elgala, Hany Ayyash, Moussa Almajali, Sufyan El-Khazali, Reyad Electronic and Electrical Engineering Department University of Cambridge United Kingdom Electrical and Computer Engineering Department University at Albany-State University of New York United States Artificial Intelligence Research Center Al Ain University Al Ain United Arab Emirates Telecommunications Engineering Department Yarmouk University Irbid Jordan Department of Computing Information and Technology Chicago State University ChicagoIL United States Department of Computer Science Princess Sumaya University for Technology Amman Jordan Electrical Engineering and Computer Science Department Khalifa University Abu Dhabi United Arab Emirates

Advancements in unmanned aerial vehicle (UAV) technology, along with indoor hybrid LiFi-WiFi networks (HLWN), promise the development of cost-effective, energy-efficient, adaptable, reliable, rapid, and on-demand HLWN-capable indoor flying networks (IFNs). To achieve this, a unified physical layer (UniPHY) capable of simultaneous control communication, data transfer, and sensing is crucial. However, traditional block-based decoders, designed independently for LiFi and WiFi, perform poorly in complex and hybrid LiFi-WiFi-enabled UniPHY systems. In this study, we propose an end-to-end learning framework based on convolutional neural networks (CNNs) for UniPHY, which can be trained to serve hybrid LiFi-WiFi transmissions to improve error performance and simplify UAV hardware. In this work, the performance of the proposed framework is assessed and compared with that of the conventional independent block-based communication system. Furthermore, a comprehensive summary of optimal hyper-parameters for efficient training of our learning framework has been provided. It is shown that, with optimal hyper-parameters, the proposed CNN-based framework outperforms the conventional block-based approach by providing a signal-to-noise ratio gain of approximately 7 dB for the LiFi channel and 23 dB for the WiFi channel. In addition, we evaluate the complexity and training convergence for loss and accuracy. © 2024 The Authors

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

A Reduced State Space Generation Method for Concurrent Systems Based on CPN-PR Model

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2024年第6期44卷 2328-2342页

作者： Zhong, Wenjie Sun, Tao Zhou, Jian-Tao Wang, Zhuowei Song, Xiaoyu Inner Mongolia Engineering Laboratory for Big Data Analysis Technology College of Computer Science Inner Mongolia University Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Hohhot010000 China Guangdong University of Technology School of Computer Science and Technology Guangzhou China Portland State University Department of Electrical and Computer Engineering PortlandOR97207 United States

Colored Petri Nets (CPNs) provide descriptions of the concurrent behaviors for software and hardware. Model checking based on CPNs is an effective method to simulate and verify the concurrent behavior in system design. However, the model checking method traverses the full state space, which suffers from the state space explosion problem. A reduced state space generation method related to the property of concurrent systems is proposed. Specifically, we extend CPNs to define a property-related model (CPN-PR) and give a property-related analysis method whose results can be used to generate the CPN-PR model. A reduced state space generation method is developed based on enabled binding element filtering rules. The stutter trace equivalence between the state spaces of CPN and CPN-PR has been proven by showing that the reduced state space may not change the model checking result. A comparison experiment is conducted to demonstrate the effectiveness of our method. © 1982-2012 IEEE.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Fast Symmetric Eigenvalue Decomposition via WY Representation on Tensor Core 23

Fast Symmetric Eigenvalue Decomposition via WY Representatio...

引用

28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, PPoPP 2023

作者： Zhang, Shaoshuai Shah, Ruchi Ootomo, Hiroyuki Yokota, Rio Wu, Panruo Department of Computer Science University of Houston TX United States Global Scientific Information and Computing Center Tokyo Institute of Technology Tokyo Japan

ISBN: (纸本)9798400700156

Symmetric eigenvalue decomposition (EVD) is a fundamental analytic and numerical tool used in many scientific areas. The state-of-the-art algorithm in terms of performance is typically the two-stage tridiagonalization method. The first stage in the two-stage tridiagonalization is called successive band reduction (SBR), which reduces a symmetric matrix to a band form, and its computational cost usually dominates. When Tensor Core (specialized matrix computational accelerator) is used to accelerate the expensive EVD, the conventional ZY-representation-based method results in suboptimal performance due to unfavorable shapes of the matrix computations. In this paper, we propose a new method that uses WY representation instead of ZY representation (see Section 3.2 for details), which can provide a better combination of locality and parallelism so as to perform better on Tensor Cores. Experimentally, the proposed method can bring up to 3.7x speedup in SBR and 2.3x in the entire EVD compared to state-of-the-art implementations. © 2023 ACM.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Analysis of Predictive Models for Revealing Household Characteristics using Smart Grid Data

Analysis of Predictive Models for Revealing Household Charac...

引用

2023 IEEE PES Innovative Smart Grid Technologies Europe, ISGT EUROPE 2023

作者： Aly, Hussein Al-Ali, Abdulaziz Al-Ali, Abdulla Malluhi, Qutaibah College of Engineering Department of Computer Science and Engineering Qatar University Doha Qatar Kindi Center for Computing Research Qatar University Doha Qatar

ISBN: (纸本)9798350396782

The Smart Grid Advanced Metering Infrastructure (AMI) has revolutionized the smart grid network, generating vast amounts of data that can be utilized for diverse objectives, one of which is Household Characteristics Classification (HCC). This can help the utility provider profile their customers and tailor their services to meet customer needs. To accomplish this task, we evaluated multiple Machine learning HCC models, with a focus on CNN-based models due to their wide popularity in the field of smart grid signal classification. We evaluated 1D and 2D variants of four different CNN architectures. Our experimental analysis revealed that ResNet-based models achieved the best performance on the task of HCC. Also, we found that 2D models tends to perform better than 1D variants. © 2023 IEEE.

关键词： CNN architectures Convolutional Neural Network Electricity Data Private Smart Grid Smart Grid Data Socio-demographic Classification

来源：评论

学校读者我要写书评

暂无评论

Feature Enhancer Segmentation Network (FES-Net)for Vessel Segmentation

Feature Enhancer Segmentation Network (FES-Net)for Vessel Se...

引用

2023 International Conference on Digital Image computing: Techniques and Applications, DICTA 2023

作者： Khan, Tariq M. Arsalan, Muhammad Iqbal, Shahzaib Razzak, Imran Meijering, Erik School of Computer Science & Engineering Unsw Sydney Australia Qatar University Kindi Center for Computing Research Doha2713 Qatar Department of Electrical and Computer Engineering Islamabad Pakistan

ISBN: (纸本)9798350382204

Diseases such as diabetic retinopathy and age-related macular degeneration pose a significant risk to vision, highlighting the importance of precise segmentation of retinal vessels for tracking and diagnosis of progression. However, existing vessel segmentation methods that heavily rely on encoder-decoder structures struggle to capture contextual information about retinal vessel configurations, leading to challenges in reconciling semantic disparities between encoder and decoder features. To address this, we propose a novel feature enhancement segmentation network (FES-Net) that achieves accurate pixel-wise segmentation without requiring additional image enhancement steps. FES-Net directly processes the input image and utilizes four prompt convolutional blocks (PCBs) during downsampling, complemented by a shallow upsampling approach to generate a binary mask for each class. We evaluate the performance of FES-Net on four publicly available state-of-the-art datasets: DRIVE, STARE, CHASE, and HRF. The evaluation results clearly demonstrate the superior performance of FES-Net compared to other competitive approaches documented in the existing literature. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU

A High-Performance Accelerator for Super-Resolution Processi...

引用

作者： Zhao, Wenqian Bai, Yang Sun, Qi Li, Wenbo Zheng, Haisheng Jiang, Nianjuan Lu, Jiangbo Yu, Bei Wong, Martin D. F. Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Heterogeneous Computing Center SmartMore Corporation Limited Hong Kong

Over the past few years, super-resolution (SR) processing has achieved astonishing progress along with the development of deep learning. Nevertheless, the rigorous requirement for real-time inference, especially for video tasks, leaves a harsh challenge for both the model architecture design and the hardware-level implementation. In this article, we propose a hardware-aware acceleration on embedded GPU devices as a full-stack SR deployment framework. The most critical stage with dictionary learning applied in SR flow was analyzed in details and optimized with a tailored dictionary slimming strategy. Moreover, we also delve into the programming architecture of hardware while analyzing the model structure to optimize the computation kernels to reduce inference latency and maximize the throughput given restricted computing power. In addition, we further accelerate the model with 8-bit integer inference by quantizing the weights in the compressed model. An adaptive 8-bit quantization flow for SR task enables the quantized model to achieve a comparable result with the full-precision baselines. With the help of our approaches, the computation and communication bottlenecks in the deep dictionary learning-based SR models can be overcome effectively. The experiments on both edge embedded device NVIDIA NX and 2080Ti prove that our framework exceeds the performance of state-of-the-art NVIDIA TensorRT significantly and can achieve real-time performance. © 2023 IEEE.

关键词： Graphics processing unit

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：