检索结果-内蒙古大学图书馆

2022 International Conference on Interdisciplinary Research in Technology and Management, IRTM 2022

作者： Sengupta, Ramita Poddar, Aditya Birla Institute Of Technology And Science Data Science And Engineering Pilani India Institute Of Engineering & Management Computer Science Engineering Kolkata India

ISBN: (纸本)9781665478861

As Microfinance operations are focused in financially under-penetrated low-income regions and have responsibilities of impact investments, they focus on the financial inclusion of the underserved. As the customers served by these organizations are part of the most vulnerable section of society, it is imperative to understand the different aspects of poverty that affect the financial health of a potential or existing debtor. United nations have recognized that eradicating poverty and other deprivations must go hand-in-hand with global strategies to improve health and education, to diminish inequality and boost economic growth. Till now, since the analysis of the creditworthiness of the customer or a group was mostly dependent on the income data and credit history, loan products were also designed depending only on these aspects. Taking account of the different social or economic aspects while screening a new business area or designing their loan products has become crucial for the Microfinance sector. The objective of this research is to predict and rate the depth of multidimensional poverty of the residents of a geographical area depending upon the deprivation faced by residents and to build a product recommendation system which can help in alleviating the deprivations faced by the customer. The dataset used was obtained from the MPI website for 2018. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Sketch2Human: Deep Human Generation with Disentangled Geometry and Appearance Constraints

引用

IEEE Transactions on Visualization and computer Graphics 2024年 PP卷 1-14页

作者： Qu, Linzi Shang, Jiaxiang Ye, Hui Han, Xiaoguang Fu, Hongbo School of Creative Media City University of Hong Kong Hong Kong Department of Computer Science & Engineering HKUST Hong Kong Shenzhen Research Institute of Big Data Chinese University of Hong Kong Shenzhen China

Geometry- and appearance-controlled full-body human image generation is an interesting but challenging task. Existing solutions are either unconditional or dependent on coarse conditions (e.g., pose, text), thus lacking explicit geometry and appearance control of body and garment. Sketching offers such editing ability and has been adopted in various sketch-based face generation and editing solutions. However, directly adapting sketch-based face generation to full-body generation often fails to produce high-fidelity and diverse results due to the high complexity and diversity in the pose, body shape, and garment shape and texture. Recent geometrically controllable diffusion-based methods mainly rely on prompts to generate appearance. It is hard to balance the realism and the faithfulness of their results to the sketch when the input is coarse. This work presents Sketch2Human, the first system for controllable full-body human image generation guided by a semantic sketch (for geometry control) and a reference image (for appearance control). Our solution is based on the latent space of StyleGAN-Human with inverted geometry and appearance latent codes as input. Specifically, we present a sketch encoder trained with a large synthetic dataset sampled from StyleGAN-Human's latent space and directly supervised by sketches rather than real images. Considering the entangled information of partial geometry and texture in StyleGAN-Human and the absence of disentangled datasets, we design a novel training scheme that creates geometry-preserved and appearance-transferred training data to tune a generator to achieve disentangled geometry and appearance control. Although our method is trained with synthetic data, it can also handle hand-drawn sketches. Qualitative and quantitative evaluations demonstrate the superior performance of our method to state-of-the-art methods. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Investigating the Utility of data Mining for Automated Credit Scoring 15

Investigating the Utility of Data Mining for Automated Credi...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Yadav, Dhyan Garima Soni, Rudransh Anandhasilambarasan, D. Sasirekha, R. Prema, S. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Karnataka Bangalore India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore641021 India Department of Computer Science and Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai127 India Department of Artificial Intelligence & Data Science Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9798350370249

data mining is a powerful device for automatic credit scoring. This paper will look into the application of statistics mining for automated credit score scoring by discussing its advantages and downsides. The form may even look at cutting-edge research in the location and discuss the demanding situations that information mining techniques pose while used for automatic credit score scoring. Similarly, the paper will provide pointers on how statistics mining techniques can improve the effectiveness of computerized credit score scoring. Subsequently, a precis of the paper's conclusions and implications for future studies could be supplied. © 2024 IEEE.

关键词： Conclusions Implications Improve Information Scoring

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing COVID-19 Diagnosis with Radiographic Images and Deep Learning: A Paradigm Shift in Healthcare

Revolutionizing COVID-19 Diagnosis with Radiographic Images ...

引用

2023 IEEE International Conference on Next Generation Electronics, NEleX 2023

作者： Mohanaprakash, T.A. Saranya, S. Abinaya, M. Rajheshwari, K.C. Elangovan, D. Gobinath, M. Panimalar Engineeering College Department of Computer Science and Engineering Chennai India Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Chennai India Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India Sona College of Technology Department of Computer Science and Engineering TamilNadu Salem India Sri Manakula Vinayagar Engineering College Departement of Computer and Communication Engineering Puducherry India

ISBN: (纸本)9798350319088

Amid the relentless battle against the COVID-19 pandemic, a cadre of researchers and scientists is diligently crafting innovative tools to expedite diagnosis and treatment. One standout innovation is the integration of radiographic images and deep convolutional neuronal networks (CNN), offering deeper insights into COVID-19. Early, accurate diagnosis is paramount in managing the COVID-19 crisis. It not only facilitates timely treatment but also curbs the virus's spread. The amalgamation of radiographic images and advanced machine learning techniques emerges as a transformative force. Traditional COVID-19 diagnostics rely heavily on molecular tests, like Polymerase Chain Reaction (PCR) tests. While highly accurate, these tests often involve protracted processing times and substantial resource demands. They may also produce false negatives in early infections. Radiographic imaging, especially chest X-rays, addresses these limitations. Researchers have harnessed deep convolutional neuronal networks, specialized for image analysis, to create an innovative diagnostic platform. This platform meticulously scrutinizes chest X-ray images, distinguishing COVID-19 pneumonia from other forms with exceptional precision. The deep CNN model undergoes intensive training on a diverse dataset, including chest X-rays from both COVID-19-positive and COVID-19-negative patients. It employs intricate processes of feature extraction and pattern recognition, discerning subtle nuances indicative of COVID-19-related lung abnormalities. This proficiency empowers the model to categorize new chest X-ray images, assisting radiologists in decision-making. The merits of this groundbreaking approach are multifaceted. Foremost is the substantial reduction in diagnosis time. Unlike molecular tests, which can take hours, chest X-ray analysis yields results within minutes, facilitating swift patient triage. It holds particular promise in resource-constrained settings where molecular testing may be scarc

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Joint Routing and Scheduling for In-Vehicle Networks: A Deterministic Perspective

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Wang, Wenxun Wang, Wenyong Yu, Haisheng Wu, Bochun Zou, Sai Ni, Wei Zhang, Ji School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China International Institute of Next Generation Internet Macau University of Science and Technology Macau China State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China College of Big Data and Information Engineering Guizhou University Guiyang China Data61 Business Unit CSIRO Canberra ACT Australia PA Company SC Branch China Telecom Co. LTD Chendu China

Deterministic transmission refers to the guaranteed delivery of data to its destination within a specific time frame along an optimal route, making it an indispensable prerequisite for the operation of autonomous vehicles. The in-vehicle networks (IVNs) face significant challenges in the deterministic transmission of large volumes of perception and control data from and to various vehicle components. In this paper, the cooperative scheduling and routing problem among multi-area control units (ACUs) in IVN is discussed from the view of deterministic transmission, and a ResVmix method is proposed to find the optimal two-layer assignment with ACU cooperation. The multi-cycle queuing and forwarding (multi-CQF) mechanism is employed to schedule the perceived data according to different quality of service (QoS) requirements. The cooperation among multiple ACUs enables deterministic routing of data. The two-layer optimization problems on multi-CQF and ACU are formulated as a+ decentralized partially observable Markov decision processes (Dec-POMDP) and solved using the enhanced multi-agent deep reinforcement learning (MADRL) method. Simulation results demonstrate that ResVmix significantly enhances the deterministic transmission performance of IVN. Compared to traditional shortest path algorithms and state-of-the-art MADRL methods, ResVmix achieves a 22.4% increase in arrival rate and a 20.1% increase in confirmed arrivals, respectively. IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Interactive Blood Bank Repository: Django AWS Approach 5

Interactive Blood Bank Repository: Django AWS Approach

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Sujatha, E. Manickavasagan, V. Lakshminarayanan, S. Ani Minisha, R. Rekha, K.S. Loganathan, V. Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu India Department of Computer Science and Business Systems Sri Sairam Engineering College Tamil Nadu India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu India Department of Information Technology Saveetha Engineering College Tamil Nadu India Department of Artificial Intelligence and Data Science Vel Tech Multi Tech Dr Rr and Dr Sr Engineering College Tamil Nadu India

ISBN: (纸本)9798350385649

Everyday, there are a growing number of people who require blood transfusions and there is no substitute for human blood. The secure blood donors are voluntary non-remunerated blood donors from risk populations. Donors in India and across the globe are three types namely, Voluntary donors, Professional donors and replacement donors. The deadline-driven web framework that supports Django's clean, practical design and speedy development. The existing system has a manual work restriction. This has restrictions on securely controlling the task for timely results declaration, and has a significant resource consumption. Web-based blood donation is the coordination of the supply and demand of blood through an online portal. The main goal of this research study is to give blood donors and blood searchers an online platform and to develop an engaging method of connecting the two groups. The suggested system provides a great deal of information regarding blood types, blood supply, and blood donation specifics to raise awareness among the public. Additionally, other system features like password-based security protection, report generation, chat functionality, and stock shortages can even improve the management tasks by streamlining them. © 2024 IEEE.

关键词： Economics

来源：评论

学校读者我要写书评

暂无评论

Mathematical Expressions in Software engineering Artifacts 23

Mathematical Expressions in Software Engineering Artifacts

引用

6th ACM India Joint International Conference on data science and Management of data, CODS-COMAD 2023

作者： Sur, Tanuj Jaisswal, Aaditree Vinayakarao, Venkatesh Data Science Chennai Mathematical Institute India Computer Engineering MKSSS's Cummins College of Engineering for Women Pune India

ISBN: (纸本)9781450397988

Mathematical expressions are required not only for numerical calculations but also for discussions and documentation. They play a significant role in providing clarifications and disambiguation of ideas, concepts and definitions. Software engineering artifacts such as source code, documentation and bug reports have mathematical expressions in them. Our experiments, with a commit message generation tool, suggest that mathematical expressions present in the input data affect the tool's accuracy. To help future research in this direction, we have constructed and shared a dataset of bug reports with both automated and manually annotated mathematical expressions. We have also shared a tool () to identify mathematical expressions. Our data set contains 2,040,120 bug reports from 10 different projects. We have used our tool to annotate all of these bug reports. From each project, we have also manually annotated 1000 bug reports. We annotated the dataset with the objective of developing toolkits to identify mathematical expressions in software engineering artifacts. Finally, we have made a case for future work to deal with mathematical expressions when improving software engineering tasks, especially those that use bug reports. © 2023 ACM.

关键词： Software engineering

来源：评论

学校读者我要写书评

暂无评论

Emotion, Age and Gender Prediction Through Masked Face Inpainting 26th

Emotion, Age and Gender Prediction Through Masked Face Inpa...

引用

26th International Conference on Pattern Recognition, ICPR 2022

作者： Islam, Md Baharul Hosen, Md Imran Department of Computer Engineering Bahcesehir University Istanbul Turkey College of Data Science and Engineering American University of Malta Cospicua Malta

ISBN: (纸本)9783031376597

Prediction of gesture and demographic information from the face is complex and challenging, particularly for the masked face. This paper proposes a deep learning-based integrated approach to predict emotion and demographic information for unmasked and masked faces, consisting of four sub-tasks: masked face detection, masked face inpainting, emotion, age, and gender prediction. The masked face detector module provides a binary decision on whether the face mask is available or not by applying pre-trained MobileNetV3. We use the inpainting module based on U-Net embedding with ImageNet weights to remove the face mask and restore the face. We use the convolutional neural networks to predict emotion (e.g., happy, angry). Besides, VGGFace-based transfer learning has been used to predict demographic information (e.g., age, gender). Extensive experiments on five publicly available datasets: AffectNet, UTKFace, FER-2013, CelebA, and MAFA, show the effectiveness of our proposed method to predict emotion and demographic identification through masked face reconstruction. © 2023, Springer Nature Switzerland AG.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Optoelectronic device based failure management using content based multispectral image retrieval and deep learning model

引用

Optical and Quantum Electronics 2024年第2期56卷 1-19页

作者： Bhukya, Raghuram Arunsundar, B. Tatini, Narendra Babu Sadala, Triveni Mohan Elshafie, Hashim Qamar, Shamimul Deaprtment of Computer Science and Engineering Kakatiya Institute of Technologey and Science Telangana Warangal India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chengalpattu Kattankulathur India Department of Internet of Things Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur India Department: CS & AI SR UNIVERSITY Telungana Warangal India Department of Computer Engineering College of Computer Science King Khalid University Main Campus Al Farah Abha 61421 Saudi Arabia Computer Science and Engineering College of Sciences and Arts King Khalid University Dhahran Al Janoub Campus Abha 64261 Saudi Arabia

The need for optoelectronic devices is growing right now, but the production of these devices is having a difficult time keeping up with the advancement of the machinery, instruments, and manufacturing techniques they support. Pictures from big, unlabeled image collections are commonly retrieved using a technique called content-based image retrieval (CBIR). The availability of photographs is also growing as internet growth and transmission networks increase. This study suggests brand-new image retrieval methods for multispectral images used in Optoelectronic device monitoring that are based on image segmentation and classification methods with deep learningtechniques for failure management. Optoelectronic device Monitoring field-based multispectral images were used as the input, which was then processed for noise removal, resizing, and *** c-means clustering-based image segmentation was used to divide up this processed image into its component parts. Following that, a hybrid multilayer transfer learning perception was used to classify the clustered segmented picture. The proposed technique has an accuracy of 95%, precision of 85%, recall of 75%, F-1 score of 63%, error rate of 51%, MAP of 55%;existing MRCN accuracy of 85%, precision of 75%, recall of 63%, F-1 score of 55%, error rate of 45%, MAP of 51%, OC-LBP accuracy of 89%, the precision of 79%, recall of 71%, F-1 score of 59%, error rate of 49%, MAP of 53%. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Classification Deep learning Failure management Multispectral image retrieval Optoelectronic device Monitoring Segmentation

来源：评论

学校读者我要写书评

暂无评论

Real-World Wireless Network Modeling and Optimization:From Model/data-Driven Perspective

引用

Chinese Journal of Electronics 2022年第6期31卷 991-1012页

作者： LI Yang ZHANG Shutao REN Xiaohui ZHU Jianhang HUANG Jiajie HE Pengcheng SHEN Kaiming YAO Zhiqiang GONG Jie CHANG Tsunghui SHI Qingjiang LUO Zhiquan Shenzhen Research Institute of Big Data Pengcheng Lab School of Science and Engineering The Chinese University of Hong Kong (Shenzhen) College of Mathematics and Computational Sciences Xiangtan University School of Computer Science and Engineering Sun Yat-Sen University School of Software Engineering Tongji University

With the rapid development of the fifth-generation wireless communication systems, a profound revolution in terms of transmission capacity, energy efficiency, reliability, latency, and connectivity is highly expected to support a new batch of industries and applications. To achieve this goal, wireless networks are becoming extremely dynamic, heterogeneous, and complex. The modeling and optimization for the performance of realworld wireless networks are extremely challenging due to the difficulty to predict the network performance as a function of network parameters, and the prohibitively huge number of parameters to optimize. The conventional network modeling and optimization approaches rely on drive test, trial-and-error, and engineering experience,which are labor intensive, error-prone, and far from optimal. On the other hand, while the research community has spent significant efforts in understanding the fundamental limits of radio channels and developing physical layer techniques to operate close to it, very little is known about the performance limits of wireless networks, where millions of radio channels interact with one another in complex manners. This paper reviews the very recent mathematical and learning based techniques for modeling and optimizing the performance of real-world wireless networks in five aspects, including channel modeling, user demand and traffic modeling, throughput modeling and prediction, network parameter optimization, and IRS empowered performance optimization, and also presents the corresponding notable performance gains.

关键词： network parameter optimization telecommunication computing optimisation mathematical techniques wireless channels performance optimization learning based techniques telecommunication traffic mathematical analysis physical layer techniques channel modeling wireless network modeling fifth generation wireless communication systems learning (artificial intelligence) model-data-driven perspective IRS empowered performance optimization radio channels traffic modeling radio networks

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：