检索结果-内蒙古大学图书馆

IEEE Symposium on High-Performance computer Architecture

作者： Jiwon Lee Gun Ko Myung Kuk Yoon Ipoom Jeong Yunho Oh Won Woo Ro Department of Electrical and Electronic Engineering Yonsei University Seoul Korea Department of Computer Science and Engineering Ewha Womans University Seoul Korea Department of System Semiconductor Engineering Yonsei University Seoul Korea School of Electrical Engineering Korea University Seoul Korea

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Virtual memory, with the support of address translation hardware, is a key technique in expanding programmability and memory management in GPUs. However, the nature of the GPU execution model heavily pressures its translation hardware, particularly due to a discrepancy in the behavior of page table walkers and thousands of concurrently running threads. In GPU workloads, multiple threads simultaneously access a number of pages necessitating a substantial number of translations whereas each walker handles only a single walk request at a time. Such a limitation significantly increases the queueing latency of walk requests, which we observe as a major bottleneck for servicing page table walks in GPUs. To tackle this challenge, we investigate a design of page walkers that facilitates multiple walk requests to be handled together in batches. Then, we make the following observations: 1) allowing a page walker to issue beyond a single memory request significantly improves the throughput of walkers, and 2) GPU applications tend to concurrently access pages in wide address ranges. By leveraging the above implications, we propose Marching Page Walks (MPW) that effectively mitigate the contention in GPU page table walkers. MPW scans pending walk requests to identify ones that can be grouped together. Then, MPW batches these requests and concurrently handles them by issuing multiple memory instructions. Experiments show that MPW reduces the queueing latency of page walks by 86.7% and improves GPU performance by 55.6% over the baseline design.

关键词： Translation Filters Instruction sets Memory management Graphics processing units Throughput Hardware Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Joint Deep Learning for Improved Myocardial Scar Detection from Cardiac MRI

Joint Deep Learning for Improved Myocardial Scar Detection f...

引用

IEEE International Symposium on Biomedical Imaging

作者： Jiarui Xing Shuo Wang Kenneth C. Bilchick Amit R. Patel Miaomiao Zhang Department of Electrical and Computer Engineering University of Virginia USA School of Medicine University of Virginia Health System USA Department of Computer Science University of Virginia USA

Automated identification of myocardial scar from late gadolinium enhancement cardiac magnetic resonance images (LGE-CMR) is limited by image noise and artifacts such as those related to motion and partial volume effect. This paper presents a novel joint deep learning (JDL) framework that improves such tasks by utilizing simultaneously learned myocardium segmentations to eliminate negative effects from non-region-of-interest areas. In contrast to previous approaches treating scar detection and myocardium segmentation as separate or parallel tasks, our proposed method introduces a message passing module where the information of myocardium segmentation is directly passed to guide scar detectors. This newly designed network will efficiently exploit joint information from the two related tasks and use all available sources of myocardium segmentation to benefit scar identification. We demonstrate the effectiveness of JDL on LGE-CMR images for automated left ventricular (LV) scar detection, with great potential to improve risk prediction in patients with both ischemic and non-ischemic heart disease and to improve response rates to cardiac resynchronization therapy (CRT) for heart failure patients. Experimental results show that our proposed approach outperforms multiple state-of-the-art methods, including commonly used two-step segmentation-classification networks, and multitask learning schemes where subtasks are indirectly interacted.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Few-Shot Relation Extraction via Representation Learning and Domain Adaptation

arXiv

引用

arXiv 2022年

作者： Yuan, Zhongju Wang, Zhenkun Li, Genghui School of System Design and Intelligent Manufacturing Department of Computer Science and Engineering

Few-shot relation extraction aims to recognize novel relations with few labeled sentences in each relation. Previous metric-based few-shot relation extraction algorithms identify relationships by comparing the prototypes generated by the few labeled sentences embedding with the embeddings of the query sentences using a trained metric function. However, as these domains always have considerable differences from those in the training dataset, the generalization ability of these approaches on unseen relations in many domains is limited. Since the prototype is necessary for obtaining relationships between entities in the latent space, we suggest learning more interpretable and efficient prototypes from prior knowledge and the intrinsic semantics of relations to extract new relations in various domains more effectively. By exploring the relationships between relations using prior information, we effectively improve the prototype representation of relations. By using contrastive learning to make the classification margins between sentence embedding more distinct, the prototype’s geometric interpretability is enhanced. Additionally, utilizing a transfer learning approach for the cross-domain problem allows the generation process of the prototype to account for the gap between other domains, making the prototype more robust and enabling the better extraction of associations across multiple domains. The experiment results on the benchmark FewRel dataset demonstrate the advantages of the suggested method over some state-of-the-art approaches. © 2022, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Real Time Flower Identification by Artificial Intelligence

Real Time Flower Identification by Artificial Intelligence

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Moshiur Rahman Taushik Ahmed Joy Samia Akter Abdus Sattar Department of Management Information System Daffodil International University Daffodil Smart City Dhaka Department of Electrical And Computer Engineering North South University Bashundhara Dhaka Department of Computer Science & Engineering Daffodil International University Daffodil Smart City Dhaka

In the realm of flower-rich Bangladesh, the presence of these blossoms enriches our everyday experiences, whether encountered during leisurely strolls, along railway tracks, or within our gardens. However, the beauty of these flowers often remains unexplored due to our limited knowledge about their names and attributes. To address this, a project was initiated to close this gap and acquaint people with these unfamiliar yet frequently encountered blooms. Our endeavor involves an innovative mobile application that employs real-time camera recognition to identify flowers, powered by neural networks, particularly the Tensorflow-based image classifier on the Android platform. Machine learning's expansive applications in computer science have propelled our interest in this arena, specifically focusing on Convolutional Neural Networks (CNN) and Tensorflow for image classification. While our current application marks the inception, aspiration to further enrich and refine our system for the future. Our ultimate aim is to share the benefits of our work, enabling individuals to gain profound insights into the enchanting floral world that envelops them daily.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Securing IoT Networks in Healthcare for Enhanced Privacy in Wearable Patient Monitoring Devices

Securing IoT Networks in Healthcare for Enhanced Privacy in ...

引用

2024 IEEE International Conference on Intelligent systems and Advanced Applications, ICISAA 2024

作者： Tiwari, Vibha Jharbade, Nitin Chourasiya, Prashant Supraja, B. Wani, Priyanka Sujit Maurya, Rashmi Madhav Institute of Technology and Science Department of Centre for Artificial intelligence M. P. Gwalior India GGITS Dept of Computer Science & Business System M.P. Jabalpur India IES Institute of Technology and Management IES University Department of Computer Science & Engineering M.P. Bhopal462044 India Guru Nanak Institutions Technical Campus Department of CSE - AIML Hyderabad India Dr. D. Y. Patil Institute of Technology Dept. of E&TC Maharastra Pune India

ISBN: (纸本)9798331539948

The project aims to make smart patient monitoring devices more private. This is crucial to healthcare IoT network security. Strong security is needed to protect patient data in a growing digital healthcare system. Our research develops a whole security system with sophisticated encryption, user-centric identity, blockchain integration, and deep learning to detect unusual activity. As mentioned before, sophisticated patient monitoring gadgets in contemporary healthcare have increased security vulnerabilities. A powerful and adaptable security system is needed to secure patient data;hence, a multidimensional approach is studied. This study's approaches include experimental design, dataset preparation, and measure choice. The security framework uses cutting-edge cryptography, including ECC, homomorphic encryption, and blockchain. Also crucial are recognizing users based on biological features and spotting abnormalities using deep learning and LSTM networks. Mixed methods mitigate all security issues. The findings reveal that the recommended strategy boosts encryption to 256 bits. Since authentication accuracy has reached 98%, user-centered authentication approaches work. Cryptographic processes employ resources effectively, and anomaly detection rates reflect how successfully the approach detects unusual device behavior. Elliptic Curve Cryptography (ECC), which may give 256-bit encryption, is stronger than symmetric encryption (128 bits). User-centric authentication was 98% accurate, outperforming public key infrastructure (95%). With a 92% success rate, LSTM networks can predict abnormal activity in connected devices. The proposed approach performs cryptographic operations fast, with 120 operations per unit time. In conclusion, this research introduces a healthcare IoT security solution. The combined encryption, identity, blockchain, and deep learning technology is secure. The recommended solution protects patient data on personal tracking devices with greater encrypt

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Optimal Method Combining Blockchain and Multi-Agent system to Ensure Data Integrity and Deduplication in the Cloud Environment

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第10期18卷 90-105页

作者： El Ghazouani, Mohamed Ikidid, Abdelouafi Zaouiat, Charafeddine Ait Aziz, Layla Ichahane, Moulay Youssef Er-Rajy, Latifa ESIM Polydisciplinary Faculty of Sidi Bennour Chouaîb Doukkali University El Jadida Morocco Laboratory of System Analysis Information Processing and Industrial Management EST Salé Mohammed V University Salé Morocco Information Technology Laboratory National School of Applied Sciences Chouaîb Doukkali University El Jadida Morocco Computer Science Department Laboratory of Information Systems Engineering Cadi Ayyad University Marrakesh Morocco

Cloud computing (CC) refers to the transmission, storage, and processing of any type of information at a location that is not owned or controlled by the information owner. This information can be stored and accessed anytime, from anywhere, and using any device. However, several challenges threaten the deployment of cloud computing technology within organizations, including user privacy, data integrity, and managing the retention of the vast amount of data that will be stored and analyzed in this environment. In recent years, various data integrity checking systems and data storage mechanisms have been proposed to address these diverse challenges. Nevertheless, some protocols do not guarantee data confidentiality against auditors during the auditing process, while others do not provide batch auditing. Additionally, the majority of these protocols do not support the deduplication technique. Therefore, in this research work, the security features of blockchain technology and those of multi-agent systems (MAS) have prompted us to propose models that enable both data deduplication, saving storage space, and data integrity auditing, efficiently verifying the accuracy of data outsourced to CC environments. Implementation findings indicate that the suggested system is highly feasible and applicable in real-world scenarios. © 2024 by the authors of this article.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Preliminary Study on the Effect of Traffic Representation on Accuracy Degradation in Machine Learning-based IoT Device Identification

Preliminary Study on the Effect of Traffic Representation on...

引用

2022 IEEE International Conference on Computing, ICOCO 2022

作者： Aqil, Nik Afifi, Firdaus Zaki, Faiz Anuar, Nor Badrul Faculty of Computer Science and Information Technology Universiti Malaya Department of Computer System and Technology Kuala Lumpur50603 Malaysia Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Terengganu21030 Malaysia

ISBN: (纸本)9781665489966

The Internet of Things (IoT) has gained attention for its rapid growth in the past few years. IoT devices such as temperature and humidity sensors and voice controllers are implemented widely, from household appliances to industrial machines. However, with the rapid growth and benefits IoT offers, we are exposed to various security vulnerabilities, such as data breaches and IoT-specific malware. Researchers are using IoT device identification as a solution for IoT security issues. IoT device identification helps network administrators identify network traffic into its originating devices. However, researchers often overlook an important issue in IoT device identification, which is accuracy degradation over time. Thus, this paper explores the severity of accuracy degradation in IoT device identification on different traffic representation approaches, which are flow, sub-flow, and packet. This paper utilizes a private, and the UNSW IoT Traffic Traces public dataset. Based on the experimental findings, the sub-flow-based approach recorded the best overall performance, with only 8% degradation in the private dataset and 1% degradation in the public dataset. Meanwhile, even though the packet-based approach only degraded 5% on the private dataset, it recorded up to an 11% accuracy decrease in the public dataset. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Interpretable Disease Prediction from Clinical Text by Leveraging Pattern Disentanglement

Interpretable Disease Prediction from Clinical Text by Lever...

引用

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Malikeh Ehghaghi Pei-Yuan Zhou Wendy Yusi Cheng Sahar Rajabi Chih-Hao Kuo En-Shiun Annie Lee Computer Science Department University of Toronto Toronto ON Canada System Design Engineering University of Waterloo Waterloo ON Canada Electrical and Computer Engineering Department University of Tehran Tehran Iran Computer Science Department Ontario Tech University University of Toronto Toronto ON Canada

For artificial intelligence (AI) systems to be adopted in high stake human-oriented applications, they must be able to make complex decisions in an understandable and interpretable manner. While AI systems today have grown leaps and bounds in predictive power using larger datasets with more complex architectures, existing models remain ineffective at generating interpretable insights in the clinical setting. In this paper, we address the challenge of discovering interpretable insights from the clinical text for disease prediction. For this purpose, we apply the clinical notes from the electronic health records (EHR) available in the Medical Information Mart of Intensive Care III (MIMIC-III) dataset, which are labeled with the international classification of diseases (ICD9) codes. Our proposed algorithm combines interpretable text-based features with a novel pattern discovery and disentanglement algorithm. Specifically, our approach encompasses the following: (1) uncovering strong association patterns between clinical notes and diseases, (2) surpassing baseline clustering algorithms in effectively distinguishing between disease clusters, and (3) demonstrating comparable performance to baseline supervised methods in predicting diseases. Our results validate the model’s capability to strike a balance between interpretability and outcome prediction accuracy. By unveiling insightful patterns between clinical notes and diseases, our approach upholds a reasonable level of diagnostic *** relevance—This paper proposes a novel all-in-one clinical Natural Language Processing (NLP) knowledge base, which can be applied in healthcare systems to discover interpretable insights from the clinical text for predicting medical conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Positioning Control for Voice Coil Motor Using Unbalanced Multilevel Inverter Topology

Positioning Control for Voice Coil Motor Using Unbalanced Mu...

引用

International Conference on Mechatronics (ICM)

作者： Gaku Takei Hidemine Obara Ryo Haneda Takahiro Nozaki Graduate School of Science and Technology Keio University Yokohama Japan Department of Physics Electrical and Computer Engineering Yokohama National University Yokohama Japan Department of System Design Engineering Keio University Yokohama Japan

ISBN: (数字)9798331533892

ISBN: (纸本)9798331533908

This article proposes a new multi-level inverter (MLI) based on flying capacitor inverter (FCI), with focused on high-precision positioning control for a voice coil motor (VCM). Multi-level inverters (MLIs) have the characteristic that increasing the number of output voltage levels reduces the output voltage error. However, as the number of levels increases, the number of circuit elements increases, and the circuit becomes more complex. In addition, the output voltage amplitude for each level is constant in conventional inverters. As a result, such as high-precision positioning control of VCM, designing an appropriate inverter for a reference wave that contains a large amount of low-voltage components increases the number of circuit elements. Therefore, this paper proposes a MLI with two unbalanced dc-input voltages, referred to as unbalanced MLIs (UMLIs) hereinafter. This topology uses two different dc-input voltages, and it is possible to reduce the output voltage level in extremely low-voltage range compared to other voltage levels. Simulation results when the high-precision positioning control of the VCM confirm that the proposed UMLIs improves the control performance compared to the conventional FCIs with equal number of output voltage levels and uniform level widths.

关键词： Coils Low voltage Simulation Switches Multilevel inverters Motors Topology Sensors Voltage control Motion control

来源：评论

学校读者我要写书评

暂无评论

Toward High-Accuracy 3D Creation of Aviation Tools via Analysis-by-Synthesis

引用

IEEE Access 2025年 13卷 87208-87219页

作者： Mohamed Hassan, Gundu Sung Kim, Yoo Jo, Geun Sik Inha University Knowledge Management System Laboratory Department of Artificial Intelligence Engineering Incheon22212 Korea Republic of Inha University Artificial Intelligence Laboratory Department of Computer Science Engineering Incheon22212 Korea Republic of Augmented Knowledge Corporation Incheon22212 Korea Republic of

The field of education is rapidly shifting toward digital platforms;however, aviation education continues to rely heavily on traditional paper-based manuals. This persistence is largely due to the inherent complexity, scale, and high costs associated with aviation equipment, making digital transformation particularly challenging. In this paper, we utilizing the analysis-by-synthesis method is presented for multi-view 3D reconstruction of solid objects, specifically focusing on aviation tools. To facilitate this research, a custom dataset was generated using Unity, enabling controlled experimentation and performance evaluation. Comparative analysis with existing benchmarks demonstrates that, despite the intricate nature of aviation tools compared to simpler objects. The proposed architecture effectively reconstructs detailed and accurate digital replicas with 97% accuracy. This advancement has the potential to significantly enhance aviation training by providing immersive, interactive 3D content, bridging the gap between traditional training materials and cutting-edge digital education tools. © 2013 IEEE.

关键词： 3D reconstruction

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：