检索结果-内蒙古大学图书馆

Offline Writer Identification using Deep Convolution Neural Network 2

Offline Writer Identification using Deep Convolution Neural ...

2nd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and Computer Engineering, MI-STA 2022

作者： Durou, Amal M. Aref, Ibrahim A. Erateb, Suleiman El-Mihoub, Tarek A. Ghalut, Tarik Emhemmed, Adel Saad University of Tripoli Faculty of Information Technology Tripoli Libya Lancaster University School of Computing and Comms Lancaster United Kingdom Coventry University Engineering and Digital Technologies Coventry United Kingdom Jade University of Applied Sciences Department of Engineering Science Wilhelmshaven Germany University of Tripoli Electrical Engineering Department Tripoli Libya

ISBN: (数字)9781665479189

ISBN: (纸本)9781665479189

Deep convolutional neural networks (DCNN) are efficient in solving different pattern recognition problems and have been applied to extract image features (IFs). This paper investigates using deep learning (DL) techniques to improve the performance of the writer identification (WI) process. This work presents a novel approach for WI tasks by combining a DL technique with machine learning (ML). A convolutional neural network (CNN) is employed as a feature extractor along with a ML algorithm to classify those features. The standard Alex-Net model is utilized to extract IFs that located in the fully connected layers (FCLs). The support vector machine (SVM) model is selected as the classifier due to its efficient capabilities to improve identification performance (IP). The proposed model is tested using various types of the datasets, namely the Islamic Heritage Project (IHP) and Clusius. Furthermore, IAM and ICFHR-2012 datasets have been employed for benchmarking the proposed model. The results demonstrate the model achieves superior performance. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Heart Disease Prediction Using KNN and RTC Algorithm

Machine Learning Heart Disease Prediction Using KNN and RTC ...

引用

International Conference on Power, Energy, Control and Transmission Systems (ICPECTS)

作者： Senthil G. A R. Prabha M Razmah T. Veeramakali Sridevi S Yashini R Dept of Information Technology Agni College of Technology Chennai India Dept of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India Dept of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Sri Ramachandra Engineering and Technology Chennai India

ISBN: (纸本)9781665462761

Heart Disease or cardiovascular disease refers to the range of heart conditions like cardiac arrest, coronary artery disease. Heart disease can be very well hindered through certain lifestyle changes. There is a significant increase in the mortality rate recently due to the distinctive heart diseases. Machine learning uses mathematical models to work efficiently with the enormous amount of data. It plays a crucial role in medical science in the prediction of distinctive diseases. Cardiologists inspects the heart functionality using electrocardiography, computed tomography. These tests are quite expensive for a common man. Recent times, the life span of a human is guaranteed only with the support of medications. As prevention is better than the cure, machine learning helps to predict the vulnerability of a heart disease with few elemental symptoms and health factors. It is been fed by the basic data of the patients like age, sex. Machine learning helps to predict the vulnerability in advance which provides the cardiologists with great acumen for the adaption of the treatment. Machine learning algorithms have proven to produce reliable and accurate output with the help of the inputs. The algorithms used in the article include KNN and decision tree classifier which is compared to yield the desired and efficient output.

关键词： Heart Machine learning algorithms Predictive models Prediction algorithms Data models Real-time systems Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance upper bound of a Grover-mixer quantum alternating operator ansatz

引用

Physical Review A 2025年第1期111卷 012401-012401页

作者： Ningyi Xie Jiahua Xu Tiejin Chen Xinwei Lee Yoshiyuki Saito Nobuyoshi Asai Dongsheng Cai Graduate School of Science and Technology University of Tsukuba 1 Chome-1-1 Tennodai Tsukuba Ibaraki 305-8577 Japan School of Computing and Augmented Intelligence Arizona State University Tempe Arizona 85281 USA Graduate School of Systems and Information Engineering University of Tsukuba 1 Chome-1-1 Tennodai Tsukuba Ibaraki 305-8577 Japan Present address: Singapore Management University Singapore. Graduate School of Computer Science and Engineering University of Aizu Aizuwakamatsu Fukushima 965-8580 Japan School of Computer Science and Engineering University of Aizu Aizuwakamatsu Fukushima 965-8580 Japan Faculty of Engineering Information and Systems University of Tsukuba 1 Chome-1-1 Tennodai Tsukuba Ibaraki 305-8577 Japan

The quantum alternating operator ansatz (QAOA) represents a branch of quantum algorithms for solving combinatorial optimization problems. A specific variant, the Grover-mixer (GM) QAOA, ensures uniform amplitude across states that share equivalent objective values. This property makes the algorithm independent of the problem structure, focusing instead on the distribution of objective values within the problem. In this work we provide an alternative proof for the upper bound on the probability of measuring a computational basis state from a GM QAOA circuit with a given depth, which is a critical factor in QAOA cost. Using this, we derive the upper bounds for the probability of sampling an optimal solution and for the approximation ratio of maximum optimization problems, both dependent on the objective value distribution. Through numerical analysis, we link the distribution to the problem size and build the regression models that relate the problem size, QAOA depth, and performance upper bound. Our results suggest that the GM QAOA provides a quadratic enhancement in sampling probability and requires circuit depth that scales exponentially with problem size to maintain consistent performance.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Shield: A Federated Learning Approach to Combat Online Pirated Content Using Deep Fakes

Deep Shield: A Federated Learning Approach to Combat Online ...

引用

IEEE UP Section Conference on Electrical Computer and Electronics (UPCON)

作者： Anurag Sinha Nitasha Rathore Amar Nath Singh Arshroop Singh Ahmed Alkhayyat Pratyush Maheshwari IGNOU School of Computing and Information Sciences of Mathematics New Delhi India Department of Informatuon Technology Bharati Shakti Vidhyapeeth India Department of Computer Science & Engineering School of Engineering & Technology Sharda University Greater Noida Saini the Emerald Heights International School India College of technical engineering The Islamic university Najaf Iraq Gyanodaya International School India

Online piracy and the spread of deep false content have become major issues in the digital age. In order to combat the widespread distribution of unlicensed information, notably through the use of deep fake technologies, this article offers “Deep Shield,” a unique solution employing federated learning techniques. Deep Shield uses a network of decentralised nodes to spread the capabilities of distributed machine learning while protecting user data privacy. We use federated learning to let several stakeholders, including platforms, regulatory authorities, and content providers, train a powerful deep learning model together without disclosing private information. By aggregating model changes and preserving data isolation, our technique ensures privacy compliance and reduces the risk of data breaches. Our research of the Deep Shield framework's design, training procedure, and deployment tactics is thorough. On a large collection of stolen content and deep fake films, we ran comprehensive trials to assess its efficacy. The findings show that Deep Shield considerably improves the identification and deletion of illegal information while upholding a high standard of privacy protection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks

arXiv

引用

arXiv 2024年

作者： Chen, Zhuomin Zhang, Jiaxing Ni, Jingchao Li, Xiaoting Bian, Yuchen Islam, Md Mezbahul Mondal, Ananda Mohan Wei, Hua Luo, Dongsheng Knight Foundation School of Computing and Information Sciences Florida International University Miami United States New Jersey Institute of Technology Newark United States Department of Computer Science University of Houston Houston United States Visa Research United States Amazon Search A9 United States School of Computing and Augmented Intelligence Arizona State University Tempe United States

Graph Neural Networks (GNNs) have become a building block in graph data processing, with wide applications in critical domains. The growing needs to deploy GNNs in high-stakes applications necessitate explainability for users in the decision-making processes. A popular paradigm for the explainability of GNNs is to identify explainable subgraphs by comparing their labels with the ones of original graphs. This task is challenging due to the substantial distributional shift from the original graphs in the training set to the set of explainable subgraphs, which prevents accurate prediction of labels with the subgraphs. To address it, in this paper, we propose a novel method that generates proxy graphs for explainable subgraphs that are in the distribution of training data. We introduce a parametric method that employs graph generators to produce proxy graphs. A new training objective based on information theory is designed to ensure that proxy graphs not only adhere to the distribution of training data but also preserve explanatory factors. Such generated proxy graphs can be reliably used to approximate the predictions of the labels of explainable subgraphs. Empirical evaluations across various datasets demonstrate our method achieves more accurate explanations for GNNs. © 2024, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-Based Weighted Federated Machine Learning Approach for Sustainable Energy Management with IoE Integration

Fuzzy-Based Weighted Federated Machine Learning Approach for...

引用

IEEE Symposium on Systems and information Engineering Design, SIEDS

作者： Taher M. Ghazal Jamshaid Iqbal Janjua Sagheer Abbas Areej Fatima Muhammad Saleem Muhammad Adnan Khan Abdulrahman Alqarafi Computer Science Department Centre for Cyber Physical Systems Khalifa University Abu Dhabi UAE Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Selangor Malaysia School of Computer Sciences National College of Business Administration & Economics Lahore Pakistan Al-Khawarizmi Institute of Computer Science University of Engineering & Technology (UET) Lahore Pakistan Department of Computer Science Bahria University Lahore Pakistan Department of Computer Science LGU Lahore Pakistan School of Computer Science Minhaj University Lahore Pakistan School of Computing Skyline University College Sharjah UAE Riphah School of Computing and Innovation Riphah International University Lahore Pakistan College of Computer Science and Engineering Taibah University Medina Saudi Arabia

ISBN: (数字)9798350385144

ISBN: (纸本)9798350385151

The considerable surge in energy consumption due to population growth and the use of new technology has posed significant challenges to energy security and the environment. Managing energy consumption on the consumer side is crucial as the demand for energy continues to increase. Consumers need to monitor their daily usage and understand consumption standards to prepare themselves for energy efficiency and cost savings. To address these challenges, a Smart Energy Management System (SEMS) based on the Internet of Energy (IoE) has been developed. This system uses day-ahead planning and accurate energy availability forecasting to manage energy demand in a smart environment with high sustainable energy penetration. The Fuzzy based Weighted Federated Learning (FWFML) approach is integrated into the system to optimize energy management. The SEMS system monitors energy usage at the user level, and a review of management plans has been introduced to improve energy efficiency in terms of 93.5% accuracy, and 6.5% miss-rate. This research work also highlights future challenges in developing SEMS to increase energy efficiency in a more robust manner.

关键词： Energy consumption Costs Smart buildings Sociology Energy efficiency Energy management systems Surges

来源：评论

学校读者我要写书评

暂无评论

An Improved Machine Learning Technique with Effective Heart Disease Prediction System

引用

Computers, Materials & Continua 2021年第12期69卷 4169-4181页

作者： Mohammad Tabrez Quasim Saad Alhuwaimel Asadullah Shaikh Yousef Asiri Khairan Rajab Rihem Farkh Khaled Al Jaloud College of Computing and Information Technology University of BishaBisha67714Saudi Arabia King Abdulaziz City for Science and Technology P.O.Box 6086Riyadh11442Saudi Arabia College of Computer Science and Information Systems Najran UniversityNajran61441Saudi Arabia College of Engineering Muzahimiyah BranchKing Saud UniversityRiyadh11451Saudi Arabia Department of Electrical Engineering Laboratory for AnalysisConception and Control of SystemsLR-11-ES20National Engineering School of TunisTunis El Manar University1002Tunisia

Heart disease is the leading cause of death *** heart disease is challenging because it requires substantial experience and *** research studies have found that the diagnostic accuracy of heart disease is *** coronary heart disorder determines the state that influences the heart valves,causing heart *** indications of coronary heart disorder are strep throat with a red persistent skin rash,and a sore throat covered by tonsils or strep *** work focuses on a hybrid machine learning algorithm that helps predict heart attacks and arterial *** first,we achieved the component perception measured by using a hybrid cuckoo search particle swarm optimization(CSPSO)*** this perception measure,characterization and accuracy were improved,while the execution time of the proposed model was *** CSPSO-deep recurrent neural network algorithm resolved issues that state-of-the-art methods *** proposed method offers an illustrative framework that helps predict heart attacks with high *** proposed technique demonstrates the model accuracy,which reached 0.97 with the applied dataset.

关键词： Machine learning deep recurrent neural network effective heart disease prediction framework

来源：评论

学校读者我要写书评

暂无评论

LazyDB: I/O Optimization of Blockchain Storage System Based on Non-Volatile Memory

LazyDB: I/O Optimization of Blockchain Storage System Based ...

引用

information science, Parallel and Distributed Systems (ISPDS), International Conference on

作者： Yang Liu Xuran Ge Nong Xiao Zhiguang Chen Yang Ou State Key Laboratory of High-Performance Computing Institute for Quantum Information College of Computer National University of Defense Technology Changsha China School of computer science and Engineering Sun Yat-sen University Guangzhou China College of Computer National University of Defense Technology Changsha China

For the blockchain storage system, this paper proposes an I/O optimization scheme based on non-volatile memory based on the storage performance requirements of the blockchain system application. This scheme adopts the key-value separation strategy. Due to the uncertain size of transaction data, by separating the “key” and “value” of transaction data, the inherent read-write amplification problem of the LSM-Tree structure is solved. The key-value separation strategy redesigns the storage system's space management and garbage collection mechanisms. Therefore, this chapter uses the byte-addressing characteristics of non-volatile memory to build a new data storage structure, a lazy compression mechanism, and a lazy garbage collection mechanism. On this basis, this paper builds a LazyDB database system for blockchain storage. To ensure the safe and reliable operation of the blockchain system, it can make full use of the storage medium and data characteristics, reducing the blockchain reading and writing process. The I/O overhead in the storage system improves the storage performance of the system. The experimental results show that compared with the most commonly used databases, such as LevelDB and RocksDB in the blockchain system, LazyDB effectively reduces the write amplification of the system and has higher read, write, and data update performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforced Learning for Label-Efficient 3D Face Reconstruction

Reinforced Learning for Label-Efficient 3D Face Reconstructi...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Hoda Mohaghegh Hossein Rahmani Hamid Laga Farid Boussaid Mohammed Bennamoun School of Computer Science and Software Engineering University of Western Australia Australia Department of Computing and Communications Lancaster University England Information Technology Discipline Murdoch University Australia School of Engineering Electrical Electronic and Computer Engineering University of Western Australia Australia

3D face reconstruction plays a major role in many human-robot interaction systems, from automatic face authentication to human-computer interface-based entertainment. To improve robustness against occlusions and noise, 3D face reconstruction networks are often trained on a set of in-the-wild face images preferably captured along different viewpoints of the subject. However, collecting the required large amounts of 3D annotated face data is expensive and time-consuming. To address the high annotation cost and due to the importance of training on a useful set, we propose an Active Learning (AL) framework that actively selects the most informative and representative samples to be labeled. To the best of our knowledge, this paper is the first work on tackling active learning for 3D face reconstruction to enable a label-efficient training strategy. In particular, we propose a Reinforcement Active Learning approach in conjunction with a clustering-based pooling strategy to select informative view-points of the subjects. Experimental results on 300W-LP and AFLW2000 datasets demonstrate that our proposed method is able to 1) efficiently select the most influencing view-points for labeling and outperforms several baseline AL techniques and 2) further improve the performance of a 3D Face Reconstruction network trained on the full dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

JointSTNet: Joint Pre-Training for Spatial-Temporal Traffic Forecasting

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Cai, Danqi Chen, Kunwei Lin, Zhizhe Li, Duo Zhou, Teng Ling, Ying Leung, Man-Fai Shantou University Department of Computer Science Shantou China Newcastle University Department of Civil and Geospatial Engineering Newcastle upon TyneNE1 7RU United Kingdom Hainan University School of Cyberspace Security Haikou570228 China University of Electronic Science and Technology of China Yangtze Delta Region Institute Quzhou324003 China Anglia Ruskin University School of Computing and Information Science Faculty of Science and Engineering Cambridge United Kingdom

In recent years, there has been rapid development in autonomous vehicle techniques due to the increasing demands in traffic management and travel planning. Accurate spatiotemporal traffic forecasting is crucial for autonomous vehicles. However, most existing methods are task-specific and tailored for specific cities, making them hard to apply for more downstream applications. These methods fail to accurately simulate the common variation of traffic states at different locations based on their spatial distance and time interval. Compared with most existing spatiotemporal prediction baselines, this paper proposes a joint pre-training framework, named JointSTNet, to further enhance the traffic spatiotemporal prediction accuracy while reducing model complexity for traffic forecasting tasks. Firstly, unlike treating traffic spatiotemporal data on roads as independent patterns, the spatial graph capsule module constructs inter-class traffic patterns based on shared dynamics within the dynamic graph structure. Additionally, the temporal encoding gated module proposed in our work expands the temporal receptive field along the time axis. Finally, we maximize reconstruction losses to handle incomplete connections within data involving intra-cluster and inter-cluster regional semantic relationships that can be enhanced through pre-training. Experimental results on four benchmarking datasets from the real world demonstrate that JointSTNet outperforms various types of state-of-the-art baselines. © 1975-2011 IEEE.

关键词： Autonomous vehicles

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：