检索结果-内蒙古大学图书馆

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, Information and Communication Engineers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimization Models and Educational Teaching Research in Agricultural Logistics System 2

Optimization Models and Educational Teaching Research in Agr...

引用

2nd IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2023

作者： Karthick, S. Kumar, B. Anjanee Sethi, Puneet Singh, Niraj Kr Srivastava, Supriya Prasanth, P Vishnu Srm Institute of Science and Technology Department of Computer Science and Engineering Ghaziabad India Dadi Institute of Engineering and Technology Department of Electronic and Communication Engineering India Teerthanker Mahaveer University Moradabad India Amity University Amity Institute of Applied Sciences India Shoolini University Faculty of Management Sciences Solan India Mohan Babu University Tirupati India

ISBN: (纸本)9798350315905

A spic and span exhaustive disciplinesare logistics science. It is essential to the headway of the board and creation principles as well as the development of the public economy. To foster a powerful agricultural economy, the undertaking of developing new agricultural corporate substances is vital. The old techniques for agricultural item assembling and circulation are as of now not ready to fulfill the requirements of production network advancement and market informatization. To resolve the issues traditional strategies welcome, investigating new agricultural item creation and conveyance techniques is fundamental. By coordinating agricultural item store network assets, eliminating wasteful connections in the course of agricultural items, reducing expenses, accomplishing discernibility of agricultural items, and guaranteeing the quality and security of agricultural items, we make an advancement system for agricultural item supply chains, drove by enormous information specialist coops. Given this, this article proposes a model for a coordinated administration stage-based agricultural item store network, and it conducts broad research on the logistics activity rationale of the chain to give a hypothetical establishment and information support for the plan and improvement of the administration stage. © 2023 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Genetic Algorithm Framework for Efficient Solutions to Capacitated Vehicle Routing Problems 18

An Enhanced Genetic Algorithm Framework for Efficient Soluti...

引用

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Arshad, Usama Ellahie, Hamza Hasan Abideen, Zain Ul Ali, Raja Hashim BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany

ISBN: (纸本)9798350328172

Capacitated Vehicle Routing Problems (CVRPs), a widely acknowledged NP-hard issue, pertains to the optimal routing of a limited-capacity vehicle fleet to fulfill customer demand, aiming for the least possible travel distance or cost. Despite the presence of numerous heuristic and exact approaches, the combinatorial characteristic of CVRP renders it challenging, especially for large-scale instances. This research provides an in-depth exploration of utilizing Genetic Algorithms (GAs) to address Capacitated Vehicle Routing Problems (CVRPs), a recognized and intricate optimization issue in the realm of logistics and supply chain management. Our paper concentrates on the innovative usage of GAs, a category of stochastic search methodologies inspired by natural selection and genetics, to grapple with CVRP. We put forth a fresh framework grounded in GA that infuses unique crossover and mutation operations tailor-made for CVRP. Our comprehensive computational trials on benchmark datasets suggest that our GA-centric method is proficient in deriving high-standard solutions within acceptable computational durations, surpassing multiple contemporary techniques concerning solution quality and resilience. Our results also underscore the scalability of our proposed approach, marking it as a viable choice for tackling extensive, real-world CVRPs. This paper enriches the current knowledge bank by demonstrating the prowess of GAs in deciphering complicated combinatorial optimization issues, thus offering a novel viewpoint for future advancements in crafting more robust and efficient CVRP resolutions. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Development of a Wireless CPR Assistance Glove to Monitor and Guide Rescuers in Performing Cardiopulmonary Resuscitation 16

Development of a Wireless CPR Assistance Glove to Monitor an...

引用

16th IEEE Malaysia International Conference on Communication, MICC 2023

作者： Chang, Kai Han Chong, Kim Soon Tiang, Sew Sun Lim, Wei Hong Mokayef, Mastaneh Tan, Bee Sian Technology & Built Environment UCSI University Faculty of Engineering Kuala Lumpur Malaysia UCSI University Department Electrical & Electronic Engineering Kuala Lumpur Malaysia Tunku Abdul Rahman University of Management and Technology Department of Computer Science and Embedded Systems Kuala Lumpur Malaysia

ISBN: (纸本)9798350304343

Cardiopulmonary resuscitation (CPR) assistance glove represents a valuable tool for monitoring chest compressions during CPR, which is crucial for effective cardiac arrest response. By incorporating an MPU6050 accelerometer sensor and a force sensing resistor, the glove enables accurate measurement of the chest compression rate and force exerted. Preliminary testing demonstrated the glove's effectiveness in simulating chest compressions, with data collected and transmitted wirelessly to MATLAB software. Manual counting and MATLAB analysis validated the accuracy of compression rate calculations, while force sensing resistor voltage readings provided insights into the force exerted during compressions. These results highlight the glove's potential to significantly enhance the precision and quality of CPR administration, improving outcomes for cardiac arrest patients. © 2023 IEEE.

关键词： Resuscitation

来源：评论

学校读者我要写书评

暂无评论

Gaps in value-driven connectivity: A case study on connectivity challenges in Northern Europe

Gaps in value-driven connectivity: A case study on connectiv...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Pasi Karppinen Sameera Bandaranayake Lotta Haukipuro Yomn Elmistikawy Harri Saarnisaari Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland Faculty of Science University of Oulu Oulu Finland Department of Computer Science Electrical and Space Engineering Luleå University of Technology Luleå Sweden

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

Well-working Internet connectivity is a fundamental citizen right and a necessity in modern digital societies. Nevertheless, the digital divide persists and often affects rural or remote areas. To bridge the digital divide, we need to understand the specific rural use cases and challenges. This would increase understanding about problems weak Internet connectivity causes, what is required from the connectivity technology and what is needed from policymakers and regulation. The goal of this paper is to identify rural use cases and analyze consequences to future connectivity technology through a mixed-methods approach: we investigated the divide and its consequences by a questionnaire and interviews conducted in northern Europe. The study found that the main issues faced by rural internet users are related to capacity, availability, and vulnerability of internet services. These issues hinder their daily life, work activities, and expose them to system-level risks. The article discusses how these findings can inform the development of more inclusive and resilient internet connectivity solutions.

关键词： Surveys Urban areas Government Web and internet services Europe Medical services Optical fiber networks Media Optical fiber devices Digital divide

来源：评论

学校读者我要写书评

暂无评论

Robust design of IRS-Aided Multi-Group Multicast System With Imperfect CSI

Robust Design of IRS-Aided Multi-Group Multicast System With...

引用

作者： Jiang, Weiheng Xiong, Peiyun Nie, Jiangtian Ding, Zhiguo Pan, Cunhua Xiong, Zehui Chongqing University School of Microelectronics and Communication Engineering Chongqing400044 China Nanyang Technological University School of Computer Science and Engineering Jurong West639798 Singapore Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates The University of Manchester Department of Electrical and Electronic Engineering ManchesterM13 9PL United Kingdom Southeast University National Mobile Communications Research Laboratory Nanjing211189 China Singapore University of Technology and Design Pillar of Information Systems Technology and Design Tampines487372 Singapore

In this paper, the robust design for the intelligent reflective surface (IRS) assisted wireless multi-group multicast system is considered, in which two optimization design problems under two different channel state information (CSI) error models are separately discussed, i.e., the fairness-based problems and the quality-of-service (QoS)-based problems for both the bounded CSI error model and the statistical CSI error model. In order to deal with the non-convex constraints of the considered problems, i.e., bounded CSI error based constraint and statistical CSI error based constraint, S-procedure is adopted to convert the non-convex SINR constraint with bounded CSI error into linear matrix inequalities (LMIs), and the Bernstein-type inequality is utilized to transform the outage probability constraint with statistical CSI error into a second-order cone (SOC) constraint and linear inequalities. Following that, two efficient algorithms based on alternate optimization (AO) are proposed to solve the fairness problems and QoS problems, wherein the semi-definite programming (SDP), penalty convex-concave procedure (CCP) and semi-definite relaxation (SDR) are utilized. Furthermore, we analyze the complexity of the proposed algorithms. Finally, some numerical simulation results are presented to verify the effectiveness of the proposed algorithms, and the impacts of the CSI error and the discrete precision of IRS reflection phase shift on the system performance are analyzed, which provides some insights for the IRS deployment and system robust design. © 2002-2012 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Survey on Machine Learning Techniques Used for Central Serous Retinopathy Detection

Survey on Machine Learning Techniques Used for Central Serou...

引用

2023 International Conference on Advances in Computation, Communication and Information technology, ICAICCIT 2023

作者： Suba, M. Rajini, S. Nirmala Sugirtha Anand, M. Dr. Mgr Educational and Research Institute Department of Computer Science Chennai Tamil Nadu Maduravoyal India Dr. Mgr Educational and Research Institute Department of Computer Applications Chennai Tamil Nadu Maduravoyal India Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications Chennai Kattankulathur India

ISBN: (纸本)9798350344387

Central Serous Retinopathy (CSR) is an important health concern affecting millions of people worldwide, leading to vision loss and blindness. This condition is identified by abnormalities in retinal layers and fluid leakage, frequently occurring in the vicinity of the macula. The disease generates pressure inside the retinal layers, resulting in the detachment of retinal walls and subsequently causing impaired vision. As the macula is home to most of the visual sensory organs, including rods and cones, the eyesight undergoes substantial effects. Thus, early detection of CSR permits preventive actions to be taken to avoid any eye damage. While numerous physical approaches for detecting CSR have been devised previously, they have demonstrated inaccuracies and a lack of reliability. This paper examines the different algorithms, imaging modalities, and the outcomes they yield that have been devised over time for the timely detection of CSR. The research reveals that the SVM classifier has achieved a 97% accuracy rate in recognizing central serous retinopathy ailment based on OCT images. © 2023 IEEE.

关键词： Choroid Neovascularization Fundus Autofluorescence Optical Coherence Tomography image Pigment Epithelium Detachment Retinal Pigment Epithelium Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

Arabic Handwritten Document OCR Solution with Binarization and Adaptive Scale Fusion Detection

arXiv

引用

arXiv 2024年

作者： Waly, Alhossien Tarek, Bassant Feteha, Ali Yehia, Rewan Amr, Gasser Fares, Ahmed Computer Science and Engineering Departement Faculty of Engineering Egypt-Japan University of Science & Technology E-JUST Alexandria21934 Egypt Electrical Engineering Department Faculty of Engineering Benha University Cairo11629 Egypt

The problem of converting images of text into plain text is a widely researched topic in both academia and industry. Arabic handwritten Text Recognation (AHTR) poses additional challenges due to diverse handwriting styles and limited labeled data. In this paper we present a complete OCR pipeline that starts with line segmentation using Differentiable Binarization and Adaptive Scale Fusion techniques to ensure accurate detection of text lines. Following segmentation, a CNNBiLSTM-CTC architecture is applied to recognize characters. Our system, trained on the Arabic Multi-Fonts Dataset (AMFDS), achieves a Character Recognition Rate (CRR) of 99.20% and a Word Recognition Rate (WRR) of 93.75% on single-word samples containing 7 to 10 characters, along with a CRR of 83.76% for sentences. These results demonstrate the system's strong performance in handling Arabic scripts, establishing a new benchmark for AHTR *** Codes 68T10 © 2024, CC BY-NC-SA.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

NOVEL INSTANCE MINING WITH PSEUDO-MARGIN EVALUATION FOR FEW-SHOT OBJECT DETECTION 47

NOVEL INSTANCE MINING WITH PSEUDO-MARGIN EVALUATION FOR FEW-...

引用

2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022

作者： Liu, Weijie Wang, Chong Yu, Shenghao Tao, Chenchen Wang, Jun Wu, Jiafei Faculty of Electrical Engineering and Computer Science Ningbo University China School of Information and Control Engineering China University of Mining and Technology China SenseTime Research China

ISBN: (纸本)9781665405409

Few-shot object detection (FSOD) enables the detector to recognize novel objects only using limited training samples, which could greatly alleviate model's dependency on data. Most existing methods include two training stages, namely base training and fine-tuning. However, the unlabeled novel instances in the base set were untouched in previous works, which can be re-used to enhance the FSOD performance. Thus, a new instance mining model is proposed in this paper to excavate the novel samples from the base set. The detector is thus fine-tuned again by these additional free novel instances. Meanwhile, a novel pseudo-margin evaluation algorithm is designed to address the quality problem of pseudo-labels brought by those new novel instances. The experimental results on MS-COCO dataset show the effectiveness of the proposed model, which does not require any additional training samples or parameters. Our code is available at: https://***/liuweijie19980216/NimPme. © 2022 IEEE

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

design Principles for Data-Driven Decision Evaluation

引用

Procedia computer science 2024年 239卷 563-574页

作者： Nada Elgendy Tero Päivärinta Ahmed Elragal Karoliina Hannula Kaisa Puolitaival M3S Faculty of Information Technology and Electrical Engineering University of Oulu Finland Department of Computer Science Electrical and Space Engineering Luleå University of Technology Sweden Antell Oulu Finland

Human-machine collaboration has potentially led to higher quality and more informed data-driven decisions. However, evaluating these decisions is necessary to measure the benefits, as well as enable experiential learning and posterior rationalization of the results and consequences. Nevertheless, the multiplicity of human-machine collaboration modes, as well as the multi-faceted nature of data-driven decisions complicates evaluation, and evaluation solutions are lacking both in research and in practice. This is further reflected in the complexity of incorporating evaluation in the design of such data-driven decision making systems, since developers are left without theoretically grounded and practically feasible principles to guide implementation. In this paper, we propose a set of five design principles, explicated from theory and practice, for systems implementing data-driven decision evaluation as the output of design science research cycles. The design principles are: 1) multi-faceted evaluation criteria, 2) unified viewpoint, 3) collaborative rationality, 4) processual ex-post evaluation, and 5) adaptive feedback and learning loops. They are further contextualized in the case of AI-enabled menu design at Antell, an innovative pioneer in the restaurant business in Finland, and consequently evaluated by the development managers of the project. Accordingly, the design principles contribute to the knowledge base on metahuman systems and data-driven decision evaluation, by concretizing existing normative concepts into prescriptive knowledge, also guiding future research and generalizing towards a design theory. Furthermore, they provide implementable statements for designing and developing such systems in practice and can be used as a checklist to compare and evaluate existing systems.

关键词： data-driven decision making human-machine collaboration ex-post evaluation collaborative rationality design principles

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：