检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Kumari, Lalita Singh, Sukhdeep Rathore, Vaibhav Varish Singh Sharma, Anuj Department of Computer Science and Applications Panjab University Chandigarh India Punjab Moga India Computer Networking and Information Technology Division PRL Ahmedabad India

The Handwritten Text Recognition problem has been a challenge for researchers for the last few decades, especially in the domain of computer vision, a subdomain of pattern recognition. Variability of texts amongst writers, cursiveness, and different font styles of handwritten texts with degradation of historical text images make it a challenging problem. Recognizing scanned document images in neural network-based systems typically involves a two-step approach: segmentation and recognition. However, this method has several drawbacks. These shortcomings encompass challenges in identifying text regions, analyzing layout diversity within pages, and establishing accurate ground truth segmentation. Consequently, these processes are prone to errors, leading to bottlenecks in achieving high recognition accuracies. Thus, in this study, we present an end-to-end paragraph recognition system that incorporates internal line segmentation and gated convolutional layers based encoder. The gating is a mechanism that controls the flow of information and allows to adaptively selection of the more relevant features in handwritten text recognition models. The attention module plays an important role in performing internal line segmentation, allowing the page to be processed line-by-line. During the decoding step, we have integrated a connectionist temporal classification-based word beam search decoder as a post-processing step. In this work, we have extended existing LexiconNet by carefully applying and utilizing gated convolutional layers in the existing deep neural network. Our results at line and page levels also favour our new GatedLexiconNet. This study reported character error rates of 2.27% on IAM, 0.9% on RIMES, and 2.13% on READ-16, and word error rates of 5.73% on IAM, 2.76% on RIMES, and 6.52% on READ-2016 datasets. © 2024, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

TAPEMAN: Towards an Optimal Data Gathering Mechanism in Wireless Sensor Networks

引用

Chinese Journal of Electronics 2023年第4期19卷 594-598页

作者： Yu Gu Yusheng Ji Hongyang Chen Baohua Zhao Department of Computer Science University of Science and Technology of China Hefei China State Key Laboratory of Networking and Switching Technology Beijing China Information Systems Architecture Science Research Division NII Tokyo Japan Institute of Industrial Science University of Tokyo Tokyo Japan

In this paper, we study the lifetime optimization problem using a mobile sink node in a storage-constrained wireless sensor network, and propose an optimal data gathering mechanism named (TAPEMAN) which runs in three steps: first a tight upper bound of the network lifetime is derived through analysis of energy consumption, then we generate a Traveling salesman problem (TSP) solution based on a 2-approximation $O(n^{2})$ algorithm. A judgment will be made about whether this solution is optimal. If the answer is yes, TAPEMAN terminates. If not, a novel data diffusion scheme is used to distribute data to neighboring nodes, in order to avoid data leaking. We prove that under some reasonable assumptions, our algorithm can achieve this upperbound. Simulation results demonstrate the efficiency of our proposed solution and substantiate the importance of using sink mobility for energy-constrained sensor networks.

关键词： Wireless communication Wireless sensor networks Energy consumption Upper bound Simulation Traveling salesman problems Delays

来源：评论

学校读者我要写书评

暂无评论

Using Mobile Sinks in WSN: Computational Complexity and a Theoretical Bound

引用

Chinese Journal of Electronics 2023年第1期20卷 147-150页

In this paper, we study the lifetime optimization problem in wireless sensor networks using mobile sink nodes. This problem is inherently difficult since we need to consider both sink scheduling and data routing. Through a simple case study we develop a novel notation named the Placement pattern (PP) to bound traffic patterns with candidate locations. This significantly decreases the number of elements needed to be scheduled. Based on the PP, we mathematically formulate this optimization problem as a Mixed-integer non-linear programming (MINLP), which is very tough and time consuming to solve. By proving that the problem is NP-complete, we point out that instead of seeking an optimal algorithm, heuristic algorithms, especially those with performance guarantee, would be much more desirable to develop. Furthermore, in order to help identify performance gains of heuristic algorithms proposed in the future, we develop a Linear programming (LP) formulation which serves as an upper bound by adopting a reformulation and relaxation technique.

关键词： Wireless sensor networks Upper bound Heuristic algorithms Traffic control Programming Performance gain Routing

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach to Anomaly Detection Based on Traffic Monitoring for Secure Blockchain networking

A Machine Learning Approach to Anomaly Detection Based on Tr...

引用

作者： Kim, Jinoh Nakashima, Makiya Fan, Wenjun Wuthier, Simeon Zhou, Xiaobo Kim, Ikkyun Chang, Sang-Yoon Texas A&M University Computer Science Department CommerceTX75428 United States Xi'an Jiaotong-Liverpool University School of Advanced Technology Department of Communications and Networking Suzhou Jiangsu215123 China University of Colorado Department of Computer Science Colorado SpringsCO80918 United States ETRI Cybersecurity Research Division Daejeon34129 Korea Republic of

While blockchain technology provides strong cryptographic protection on the ledger and the system operations, the underlying blockchain networking remains vulnerable due to potential threats such as denial of service (DoS), Eclipse, spoofing, and Sybil attacks. Effectively detecting such malicious events should thus be an essential task for securing blockchain networks and services. Due to its importance, several studies investigated anomaly detection in Bitcoin and blockchain networks, but their analyses mainly focused on the blockchain ledger in the application context (e.g., transactions) and targets specific types of attacks (e.g., double-spending, deanonymization, etc). In this study, we present a security mechanism based on the analysis of blockchain network traffic statistics (rather than ledger data) to detect malicious events, through the functions of data collection and anomaly detection. The data collection engine senses the underlying blockchain traffic and generates multi-dimensional data streams in a periodic, real-time manner. The anomaly detection engine then detects anomalies from the created data instances based on semi-supervised learning, which is capable of detecting previously unseen patterns, and we introduce our profiling-based detection engine implemented on top of AutoEncoder (AE). Our experimental results evaluated with real and simulated traffic data support the effectiveness of our security mechanism and design choices based on the AE structure, with the approximate detection performance to the supervised learning methods only through the profiling of normal instances. The measured time complexity is sufficiently cheap to perform real-time analysis, with less than 1.4 msec for per-instance testing on a single core setting. © 2004-2012 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

HYPERPARAMETER TUNING FOR DEEP REINFORCEMENT LEARNING APPLICATIONS

arXiv

引用

arXiv 2022年

作者： Kiran, Mariam Ozyildirim, Melis Scientific Networking Division Lawrence Berkeley National Laboratory United States Department of Computer Science Cukurova University Turkey

Reinforcement learning (RL) applications, where an agent can simply learn optimal behaviors by interacting with the environment, are quickly gaining tremendous success in a wide variety of applications from controlling simple pendulums to complex data centers. However, setting the right hyperparameters can have a huge impact on the deployed solution performance and reliability in the inference models, produced via RL, used for decision-making. Hyperparameter search itself is a laborious process that requires many iterations and computationally expensive to find the best settings that produce the best neural network architectures. In comparison to other neural network architectures, deep RL has not witnessed much hyperparameter tuning, due to its algorithm complexity and simulation platforms needed. In this paper, we propose a distributed variable-length genetic algorithm framework to systematically tune hyperparameters for various RL applications, improving training time and robustness of the architecture, via evolution. We demonstrate the scalability of our approach on many RL problems (from simple gyms to complex applications) and compared with Bayesian approach. Our results show that with more generations, optimal solutions that require fewer training episodes and are computationally cheap while being more robust for deployment. Our results are imperative to advance deep reinforcement learning controllers for real-world problems. © 2022, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Highly Scalable Instruction Scheduler Design based on CPU Stall Elimination

A Highly Scalable Instruction Scheduler Design based on CPU ...

引用

2021 Zooming Innovation in Consumer Technologies Conference, ZINC 2021

作者： Sari, Alparslan Butun, Ismail University of Delaware Computer Systems and Networking Department of Electrical and Computer Engineering NewarkDE19716 United States Chalmers University of Technology Network and Systems Division Department of Computer Science and Engineering Gothenburg412 96 Sweden

ISBN: (纸本)9781665404174

In this paper, by targeting low-level code optimization, an instruction scheduler is designed and experimented with a synergistic processor unit (SPU) to show its effectiveness on a basic block and data dependency graph (DDG) called compiler instruction scheduler (CIS). In our methodology, a source C/C++ file is converted to an assembly file via spu-gcc to detect stalls in basic code blocks and CIS generates the DDG of executable code to eliminate stalls to find optimization opportunities and increase the program performance. The CIS simply shuffles the instruction sequences of the assembly code to eliminate CPU stalls in a given basic instruction block. Random and sliding window schedulers are implemented to generate a new assembly code sequence based on DDG and a basic block in parallel. Finally, this paper describes how CIS finds the optimized code sequence for a given file without any conflicts and hazards. Compared to the original code compilation process, we have shown that CIS improves the code execution metrics, and also our evaluated speedup results are found to be promising. © 2021 IEEE.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Designing a Distributed Multi-agent System for Compiler Optimization

Designing a Distributed Multi-agent System for Compiler Opti...

引用

2021 Zooming Innovation in Consumer Technologies Conference, ZINC 2021

作者： Sari, Alparslan Sahin, Cagri Butun, Ismail University of Delaware Electrical and Computer Engineering Computer Systems and Networking NewarkDE United States Gazi University Computer Engineering Software Research Group Ankara Turkey Chalmers University of Technology Computer Science and Engineering Network and Systems Division Gothenburg Sweden

ISBN: (纸本)9781665404174

This paper explores the run time performance improvements using different GCC optimization flags in program compilation. As multi-core microprocessor systems replacing legacy single-core ones, tremendous effort is needed to address to optimize the associated compilers for newly designed architectures in order to suit them for running parallel programming on multiple cores. Therefore, the aim of this paper is to address this challenge by designing an optimum distributed multi-agent system to perform compiler optimization. A multi-agent framework is adopted to utilize random and genetic algorithm-based search algorithm to find the best GCC optimization flags for a given program. The framework is highly scalable and can be extended with distributed system concept to perform code compilation in parallel to find the best-optimized code sequence in a short amount of time. The initial performance results have promising indicators which clearly show that the performance improvement is achieved. © 2021 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Pre-trained Convolutional Neural Networks and Otsu’s Multi-level Thresholding based Alzheimer’s Classification

Pre-trained Convolutional Neural Networks and Otsu’s Multi-...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Nivedhitha Mahendran P M Durai Raj Vincent Duraimurugan Samiayya Venkatesan Rajinikanth Department of Networking and Communications School of Computing Technologies SRM Institute of Science and Technology Kattankulathur Chennai India School of Computer Science and Engineering and Information Systems Vellore Institute of Technology Vellore India Department of Information Technology St. Joseph’s College of Engineering Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Division of Research and Innovation SIMATS Chennai India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Disorders affecting the brain and the nerves that supply the entire body are referred to as neurological diseases. Changes in the brain’s chemistry, structure, or electrical system can cause a variety of symptoms. Alzheimer’s disease (AD), a degenerative neurological condition that impairs cognitive function, is one example of this type of illness. The most prevalent type of dementia for which there is no effective treatment. Early detection and treatment, however, may help the patient’s lifestyle and reduce symptoms. Brain imaging techniques, including MRI, CT, PET, and others, are widely used to diagnose neurological problems. It has been discovered that the Artificial Intelligence based approaches, such as the deep learning algorithms and machine learning algorithms work well for assessing these photos and provide improved accuracy for identifying AD. In this paper, we classified AD and Control cases using four different Convolutional Neural Networks (CNN) versions. Additionally, in order to increase the accuracy of AD’s classification, we have segmented the images using Otsu’s thresholding technique. The outcomes demonstrate that, both before and after thresholding was implemented, the CNN AlexNet offers a significant improvement over the other deep learning models.

关键词： Neurological diseases Deep learning Thresholding (Imaging) Machine learning algorithms Magnetic resonance imaging Computed tomography Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Linear Convergence in Hilbert's Projective Metric for Computing Augustin Information and a Rényi Information Measure

arXiv

引用

arXiv 2024年

作者： Tsai, Chung-En Wang, Guan-Ren Cheng, Hao-Chung Li, Yen-Huan Department of Computer Science and Information Engineering National Taiwan University Taiwan Graduate Institute of Networking and Multimedia National Taiwan University Taiwan Department of Electrical Engineering Graduate Institute of Communication Engineering National Taiwan University Taiwan Department of Mathematics National Taiwan University Taiwan Center for Quantum Science and Engineering National Taiwan University Taiwan Physics Division National Center for Theoretical Sciences Taiwan Quantum Computing Centre Taiwan

Consider the problems of computing the Augustin information and a Rényi information measure of statistical independence, previously explored by Lapidoth and Pfister (IEEE Information Theory Workshop, 2018) and Tomamichel and Hayashi (IEEE Trans. Inf. Theory, 64(2):1064-1082, 2018). Both quantities are defined as solutions to optimization problems and lack closed-form expressions. This paper analyzes two iterative algorithms: Augustin's fixed-point iteration for computing the Augustin information, and the algorithm by Kamatsuka et al. (arXiv:2404.10950) for the Rényi information measure. Previously, it was only known that these algorithms converge asymptotically. We establish the linear convergence of Augustin's algorithm for the Augustin information of order α ∈ (1/2, 1) ∪ (1, 3/2) and Kamatsuka et al.'s algorithm for the Rényi information measure of order α ∈ [1/2, 1) ∪ (1,∞), using Hilbert's projective metric. Copyright © 2024, The Authors. All rights reserved.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Quantum Computing: Vision and Challenges

arXiv

引用

arXiv 2024年

作者： Gill, Sukhpal Singh Cetinkaya, Oktay Marrone, Stefano Claudino, Daniel Haunschild, David Schlote, Leon Wu, Huaming Ottaviani, Carlo Liu, Xiaoyuan Machupalli, Sree Pragna Kaur, Kamalpreet Arora, Priyansh Liu, Ji Farouk, Ahmed Song, Houbing Herbert Uhlig, Steve Ramamohanarao, Kotagiri School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Dipartimento di Matematica e Fisica Università della Campania "Luigi Vanvitelli" Italy Quantum Information Science Section Oak Ridge National Laboratory Oak RidgeTN United States Detecon International GmbH Munich Germany DB Cargo Berlin Germany Center for Applied Mathematics Tianjin University Tianjin China Department of Computer Science York Centre for Quantum Technologies University of York York United Kingdom Fujitsu Research of America Inc. Santa ClaraCA United States Information Networking Institute Carnegie Mellon University United States Cymax Group Technologies BC Canada Microsoft Schiphol Netherlands Mathematics and Computational Research Division Argonne National Laboratory IL United States Department of Computer Science Faculty of Computers and Artificial Intelligence South Valley University Hurghada Egypt Baltimore United States The University of Melbourne VIC Australia

The recent development of quantum computing, which uses entanglement, superposition, and other quantum fundamental concepts, can provide substantial processing advantages over traditional computing. These quantum features help solve many complex problems that cannot be solved otherwise with conventional computing methods. These problems include modeling quantum mechanics, logistics, chemical-based advances, drug design, statistical science, sustainable energy, banking, reliable communication, and quantum chemical engineering. The last few years have witnessed remarkable progress in quantum software and algorithm creation and quantum hardware research, which has significantly advanced the prospect of realizing quantum computers. It would be helpful to have comprehensive literature research on this area to grasp the current status and find outstanding problems that require considerable attention from the research community working in the quantum computing industry. To better understand quantum computing, this paper examines the foundations and vision based on current research in this area. We discuss cutting-edge developments in quantum computer hardware advancement and subsequent advances in quantum cryptography, quantum software, and high-scalability quantum computers. Many potential challenges and exciting new trends for quantum technology research and development are highlighted in this paper for a broader debate. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum computers

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：