检索结果-内蒙古大学图书馆

Text line recognition of dai language using statistical characteristics of texture analysis and deep gaussian process

引用

International Journal of Circuits, Systems and Signal Processing 2021年 15卷 576-585页

作者： Zhao, Jingying Dong, Na Guo, Hai Liu, Yifan Yang, Doudou College of Computer Science and Engineering Dalian Minzu University 18 LiaoheWest Road Dalian Development Zone Dalian116600 China Faculty of Electronic Information and Electrical Engineering Dalian University of Technology Dalian116023 China

—In view of the different recognition methods of Dai in different language, we proposed a novel method of text line recognition for New Tai Lue and Lanna Dai based on statistical characteristics of texture analysis and Deep Gaussian process, which can classify different Dai text lines. First, the Dai text line database is constructed, and the images are preprocessed by de-noise and size standardization. Gabor multi-scale decomposition is carried out on two Dai text line images, and then the statistical features of image entropy and average row variance feature is extracted. The multi-layers Deep Gaussian process classifier is constructed. Experiments show that the accuracy of text line classification of New Tai Lue and Lanna Dai based on Deep Gaussian process is 99.89%, the values of precision, recall and f1-score are 1, 0.9978 and 0.9989, respectively. The combination of Gabor texture analysis average row variance statistical features and Deep Gaussian process model can effectively classify the text line of New Tai Lue and Lanna Dai. Comparative experiments show that the classification accuracy of the model is superior to traditional methods, such as Gaussian Naive Bayes, Random Forest, Decision Tree, and Gaussian Process. © 2021, North Atlantic University Union NAUN. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Repairing Schemes for Tamo-Barg Codes

Repairing Schemes for Tamo-Barg Codes

引用

IEEE International Symposium on information Theory

作者： Han Cai Ying Miao Moshe Schwartz Xiaohu Tang School of Information Science and Technology Southwest Jiaotong University Chengdu China Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Japan Department of Electrical and Computer Engineering McMaster University Hamilton Ontario Canada School of Electrical and Computer Engineering Ben-Gurion University of the Negev Beer Sheva Israel

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

We study the problem of repairing erasures in locally repairable codes beyond the code locality under the rack-aware model. We devise two repair schemes to reduce the repair bandwidth for Tamo-Barg codes under the rack-aware model, by setting each repair set as a rack. The first repair scheme provides optimal repair bandwidth for one rack erasure. We then establish a cut-set bound for locally repairable codes under the rack-aware model. Using this bound we show that our second repair scheme is optimal. Furthermore, we consider the partial-repair problem for locally repairable codes under the rack-aware model, and introduce both repair schemes and bounds for this scenario.

关键词： Codes Bandwidth Maintenance engineering

来源：评论

学校读者我要写书评

暂无评论

IoT Based Human Biometric System Using Alcohol Level Detection for Driver Security 1

IoT Based Human Biometric System Using Alcohol Level Detecti...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Sinha, Anurag Kumar, Nitish Ticku, Amrita Modi, Vyom Shah, Meghal Shrivastava, Kapil School of Computing and Information Sciences Ignou New Delhi India Lovely Professional University Department of Computer Science Punjab Phagwara144001 India Bharti Vidyapeeth's College of Engineering India India Faculty of Engineering Marwadi Education Foundation Gujarat Rajkot360006 India Charotar University of Science & Technology Department of Computer Science & Engineering Gujarat 388421 India Department of Computer Engineering and Applications GLA University Mathura India

ISBN: (纸本)9798350330915

In today's society, driving after intoxication has become a major factor in traffic accidents. It is common knowledge that operating a vehicle while intoxicated is a major contributing factor in a significant number of accidents. The effects of drunk driving go beyond the drunk driver;they also affect other drivers and passengers in the same vehicle. As a result, this growing threat needs to be addressed immediately. Our project's goal is to create a system that uses the Internet of Things (IoT) to find traces of alcohol in someone's breath and apply preventive measures in order to effectively address this issue. Although there are laws against drunk driving, it is difficult to enforce them widely because law enforcement cannot constantly be present on the roads to spot drunk drivers. This restriction increases the chance of accidents significantly. In order to reduce future risks, a trustworthy system that can recognize and discourage drunk drivers is urgently needed. Drunk driving deaths are increasing, so we need to figure out how to reduce these kinds of deaths. The breath analyzing sensor used in the suggested system is the MQ-3, which calculates the breath alcohol content of an individual. The amount of alcohol that is allowed in the blood in India is 0.03. The engine won't start if the person's blood alcohol content is higher than this limit, making it impossible for them to drive. Additionally, the system will send an alert, possibly through a Raspberry Pi, to a friend or relative, providing the exact location using GPS coordinates. This notification serves as a precautionary measure to keep others informed about the situation. Implementing such a system can contribute significantly to reducing accidents related to alcohol consumption. In conclusion, detectors like the one proposed in this project hold immense significance in preventing the loss of life and property caused by reckless driving under the influence of alcohol. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Dual-Channel Nonlinear Method for Crude Copper Grade Prediction Based on LSTM-Attention and GWO-RF

A Dual-Channel Nonlinear Method for Crude Copper Grade Predi...

引用

第43届中国控制会议

作者： Qinghang Guan Chunxi Yang Xiufeng Zhang Jin Zhang Faculty of Mechanical and Electrical Engineering Kunming University of Science and Technology Yunnan International Joint Laboratory of Inteligent Control and Application of Advanced Equipment Faculty of Information Engineering and Automation Kunming University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Converter blowing is the key process method for refined copper extraction, characterized as a large-hysteresis, weakly robust, nonlinear system. The grade of crude copper directly impacts the quality and technological level of refined copper,making it essential to establish a predictive model for crude copper grade. In this paper, a new two-channel nonlinear method LAGR-ELM is proposed. Initially, wavelet denoising method is used to improve the data quality. Subsequently, the first channel is based on LSTM combined with Attention mechanism to predict the crude copper grade by using its ability to capture the hidden temporal information of the data, and the second channel employs the Grey Wolf Optimizer to optimize the Random Forest algorithm. Then, a nonlinear aggregation mechanism based on ELM is used to address the inherent shortcomings of single methods and linear combinations. The effectiveness is validated using real data from a copper smelting plant in *** comparing with eight prediction methods, the simulation results show that LAGR-ELM can achieve better prediction results.

关键词： Wavelet denoising LSTM Random forests Extreme learning machines Nonlinear combination Two-channel prediction Crude copper grade prediction

来源：评论

学校读者我要写书评

暂无评论

Whole Slide Image Annotation Support for Estimating Lesion Proportions

Whole Slide Image Annotation Support for Estimating Lesion P...

引用

International Conference on Cyberworlds

作者： Nana Takano Satoshi Nishiguchi Masahiro Toyoura Graduate School of Information Science and Technology Osaka Institute of Technology Osaka Japan Faculty of Information Science and Technology Osaka Institute of Technology Osaka Japan Department of Computer Science and Engineering University of Yamanashi Yamanashi Japan

ISBN: (数字)9798331527174

ISBN: (纸本)9798331527181

The annotation of medical images for the purpose of segmentation demands a high level of expertise and experience, and the generation of suitable datasets represents a significant challenge. In this study, we propose a method that facilitates annotation on a whole slide image (WSI) without requiring detailed specification of the lesion area. The objective is to enable annotation without the need for specialised knowledge. In particular, the WSI is divided into smaller regions for annotation purposes, with the proportion of lesions in each region being compared with reference images of similar regions, for which the proportion of lesions is known. The proportion of lesions in the reference small region image deemed to be most analogous is then designated as the annotation. The outcomes of an annotation experiment on multiple subjects based on this approach indicated that as the level of experience of the annotator increased, the variability in the accuracy rate diminished. This suggests that the annotators had acquired knowledge and skills through the process of annotation.

关键词： Image segmentation Accuracy Annotations Image annotation Lesions Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Decentralized Task Offloading and Load-Balancing for Mobile Edge Computing in Dense Networks

arXiv

引用

arXiv 2024年

作者： Yahya, Mariam Conzelmann, Alexander Maghsudi, Setareh Department of Computer Science University of Tübingen Tübingen72074 Germany Faculty of Electrical Engineering and Information Technology Ruhr-University Bochum Bochum44801 Germany

We study the problem of decentralized task offloading and load-balancing in a dense network with numerous devices and a set of edge servers. Solving this problem optimally is complicated due to the unknown network information and random task sizes. The shared network resources also influence the users' decisions and resource distribution. Our solution combines the mean field multi-agent multi-armed bandit (MAB) game with a load-balancing technique that adjusts the servers' rewards to achieve a target population profile despite the distributed user decision-making. Numerical results demonstrate the efficacy of our approach and the convergence to the target load distribution. Copyright © 2024, The Authors. All rights reserved.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Planning Data Poisoning Attacks on Heterogeneous Recommender Systems in a Multiplayer Setting

Planning Data Poisoning Attacks on Heterogeneous Recommender...

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Yeh, Chin-Yuan Chen, Hsi-Wen Yang, De-Nian Lee, Wang-Chien Yu, Philip S. Chen, Ming-Syan National Taiwan University Graduate Institute of Communication Engineering Taiwan National Taiwan University Department of Electrical Engineering Taiwan Academia Sinica Institute of Information Science Taiwan Academia Sinica Research Center for Information Technology Innovation Taiwan The Pennsylvania State University Department of Computer Science and Engineering United States University of Illinois Chicago Department of Computer Science United States

ISBN: (纸本)9798350322279

Data poisoning attacks against recommender systems (RecSys) often assume a single seller as the adversary. However, in reality, there are usually multiple sellers attempting to promote their items through RecSys manipulation. To obtain the best data poisoning plan, it is important for an attacker to anticipate and withstand the actions of his opponents. This work studies the problem of Multiplayer Comprehensive Attack (MCA) from the perspective of the attacker, considering the subsequent attacks by his opponents. In MCA, we target the Heterogeneous RecSys, where user-item interaction records, user social network, and item correlation graph are used for recommendations. To tackle MCA, we present the Multilevel Stackelberg Optimization over Progressive Differentiable Surrogate (MSOPDS). The Multilevel Stackelberg Optimization (MSO) method is used to form the optimum strategies by solving the Stackelberg game equilibrium between the attacker and his opponents, while the Progressive Differentiable Surrogate (PDS) addresses technical challenges in deriving gradients for candidate poisoning actions. Experiments on Heterogeneous RecSys trained with public datasets show that MSOPDS outperforms all examined prior works by up to 10.6% in average predicted ratings and up to 11.4% in HitRate@3 for an item targeted by an attacker facing one opponent. Source code provided in https://***/jimmy-academia/MSOPDS. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Novel Bendable Mnxca(0.90−X)Ni0.10fe2o4 Substrate Based Symmetrical Metamaterial Absorber for Rf Energy Harvesting Application to Achieve Sustainable Development Goals

SSRN

引用

SSRN 2024年

作者： Hasan, Mohammad Shakibul Islam, Mohammad Tariqul Ouda, Mohammad Alenezi, Abdulmajeed M. Soliman, Mohamed S. Samsuzzaman, Md. Department of Electrical Electronic and Systems Engineering Faculty of Engineering and Built Environment Universiti Kebangsaan Malaysia Selangor Bangi43600 Malaysia Electrical Engineering Technology College of Engineering & Technology University of Doha for Science and Technology Doha24449 Qatar Department of Electrical Engineering Faculty of Engineering Islamic University of Madinah Madinah41411 Saudi Arabia Department of Electrical Engineering College of Engineering Taif University Taif21944 Saudi Arabia Department of Computer and Communication Engineering Faculty of Computer Science and Engineering Patuakhali Science and Technology University Bangladesh

This article presents a bendable substrate MnxCa(0.90−x)Ni0.10Fe2O4 based metamaterial absorber for RF energy harvesting from Wifi frequency of 5 GHz to the achievement of the Sustainable Development Goals. The bendable metamaterial absorber (BMMA) energy harvester unit cell constructed with the physical dimension of 21 × 21 *** proposed unit cell consist of cross sign shaped resonator surrounded by circular ring resonator is located middle portion and boundary split outer ring resonator. Based on the simulation findings, the proposed BMMA energy harvester provides maximum energy harvesting efficiency of 99.42% at 5 GHz. Due to the symmetrical design, the energy harvester unit cell shows excellent angle insensitive up to 90 degrees for incident angle and polarization angle. The proposed BMMA exhibits single negative properties, and it shows excellent harvesting efficiency for various bending conditions. The lightweight, flexibility of the structure indicate that MnxCa(0.90−x)Ni0.10Fe2O4 based bendable metamaterial absorber energy harvester have significant potential for RF energy harvesting application from wifi frequency of 5 GHz and it achieve Sustainable Development Goals (SDGs), specially alignment with SDG 7 (Affordable and Clean Energy), SDG 9 (Industry, Innovation, and Infrastructure), SDG 11 (Sustainable Cities and Communities),and SDG 13 (Climate Action). © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cluster Head Selection using Dingo Optimization Algorithm in Mobile Ad Hoc Network

Cluster Head Selection using Dingo Optimization Algorithm in...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Vadakkethil Somanathan Pillai, Sanjaikanth E Kumar Pareek, Piyush Polimetla, Kiran Zanke, Pankaj Ali, Hassan Mohamed University of North Dakota School of Electrical Engineering and Computer Science Grand Forks United States Nitte Meenakshi Institute of Technology Department of Aiml Bengaluru India Adobe Inc Department. of Information Technology AustinTX United States Sapiens International Corporation The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq

ISBN: (纸本)9798350360660

Efficient Energy-Efficient Cluster Head Selection (EECHS) remains a critical issue in Mobile Ad Hoc Networks (MANETs), where the selection of an appropriate cluster head (CH) can significantly enhance power efficiency. Clustering in routing plays a vital role in optimizing MANET performance by coordinating pathways through various analytics and criteria. Nodes in MANETs form clusters to improve communication, employing strategies such as distributed clustering and cluster-based routing. Despite their application, these methods often suffer from complexity and high overhead, which compromise their *** study proposes the Dingo Optimization Algorithm (DOA) as a viable solution to the EECHS problem. DOA inherits its exploration and exploitation processes from the natural behavior of dingoes, involving techniques such as pursuing, approaching, encircling, and pestering to identify the optimal CHs. Extensive experimental research conducted on the NS2 simulator demonstrates that the proposed method achieves a packet delivery ratio (PDR) of 96%, a throughput of 240 Kbps, and an energy consumption of 21 mJ for a network with 500 nodes. The simulation results and replication findings indicate that this strategy is particularly suitable for sensitive MANET applications, outperforming existing routing tactics in terms of efficiency and effectiveness. © 2024 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Medical Diagnosis System for Malaria and Typhoid Fever Using Genetic Neuro-Fuzzy System

An Enhanced Medical Diagnosis System for Malaria and Typhoid...

引用

International Conference on Artificial Intelligence and Smart Environment, ICAISE 2022

作者： Awotunde, Joseph Bamidele Imoize, Agbotiname Lucky Salako, Dotun Patrick Farhaoui, Yousef Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Kwara State Ilorin240003 Nigeria Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Lagos100213 Nigeria STI Laboratory T-IDMS Faculty of Sciences and Techniques Moulay Ismail University of Meknès Errachidia Morocco

ISBN: (纸本)9783031262531

The major challenge of inadequate healthcare services in developing countries has been linked to the unavailability of qualified medical personnel and inefficient diagnostic techniques adopted. The advent of technology in medicine has aided the improvement of medical processes including diagnosis. Many computerized systems have been implemented over the years for medical diagnosis some of which included machine learning techniques. But the existing methods lack the power of selecting the most relevant signs and symptoms of malaria and typhoid fever. Therefore, this study develops a system capable of Malaria and Typhoid Fever diagnosis using a Genetic Algorithm, a Neuro-Fuzzy Inference System called GENFIS. In order to train the NFIS, the GA module determines the optimal set of network parameters, saves them, and then distributes them to the appropriate hidden layer nodes. The study made use of the MATLAB environment to test and evaluate the system. The accuracy performance of the proposed model revealed an accuracy of 97.2%, thus performing better than some of the existing systems. If completely adopted, the proposed approach has the potential to lessen the major issues with NFIS systems. Furthermore, it might be used to address difficult issues in different fields. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Genetic algorithms

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：