检索结果-内蒙古大学图书馆

7th Asian Conference on Pattern Recognition, ACPR 2023

作者： Wang, Yangbo Zhou, Jie Lin, Qingshui Lu, Jianglin Gao, Can National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Basic Teaching Department Liaoning Technical University Huludao125105 China College of Engineering Northeastern University BostonMA02115 United States

ISBN: (纸本)9783031476648

Self-expression learning methods often obtain a coefficient matrix to measure the similarity between pairs of samples. However, directly using all points to represent a fixed sample in a class under the self-expression framework may not be ideal, as points from other classes participate in the representing process. To alleviate this issue, this study attempts to achieve representation learning between points only coming from the same class. In practice, it is easier for data points from the same class to represent each other than that from different classes. So, when reconstructing a point, if the number of non-zero elements in the coefficient vector is limited, a model is more likely to select data points from the class where the reconstructed point lies to complete the reconstruction work. Based on this idea, we propose Sparse Subspace Clustering with the l0 inequality constraint (SSC- l0 ). In SSC- l0, the l0 inequality constraint determines the maximum number of non-zero elements in the coefficient vector, which helps SSC- l0 to conduct representation learning among the points in the same class. After introducing the simplex constraint to ensure the translation invariance of the model, an optimization method concerning l0 inequality constraint is formed to solve the proposed SSC- l0, and its convergence is theoretically analyzed. Extensive experiments on well-known datasets demonstrate the superiority of SSC- l0 compared to several state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Asset Class Market Investment Portfolio Analysis and Tracking 5

Asset Class Market Investment Portfolio Analysis and Trackin...

引用

5th International Conference on Contemporary Computing and Informatics, IC3I 2022

作者： Jadhav, Pramod A Vinotha, C. Gupta, Sushil Kumar Dhyani, Bijesh Patil, Vinod H Kumar, Rohit Department of Computer Science & Businress System College of Engineering Maharashtra Pune India Sri Krishna College of Engineering & Technology Department of MBA Tamilnadu Coimbatore India Maharashtra Pune India Graphic Era Deemed to Be University Depaertment of Management Studies Uttarakhand Dehradun India College of Engineering Department of Electronics & Telecommunication Maharashtra Pune India Lloyd Institute of Engineering and Technology Department of Humanities Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350398267

Researchers and analysts have, for a long time, taken an interest in the expectations that consumers have regarding stock marketing. There is a widespread perception that trying to forecast what will happen in the stock market is fruitless since the market behaves fundamentally like a random walk. Predicting swings in stock prices may be difficult because of the many different elements that are in play. In the short run, the showcase acts as a voting machine, but in the long run, it acts as a scale, which enables the prediction of its long-term trajectory. It seems that the application of machine learning and other technologies to the issues of inventory analysis and cost estimates is a new sector that has a lot of potential. To begin, we will present a concise introduction to stock markets and an in-depth explanation of how to make predictions regarding stock prices. The next step is for us to hone in on many of the most significant problems surrounding the precision of stock research and estimates. The fundamental, intermediate, short-term, and long-term perspectives on stocks, as well as their technical aspects, are explored. In conclusion, we highlight a few problems and investigate possible advancements that the future may hold in this sector. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Identifying Inaccurate Stories: Leveraging High Knowledge and Big Data

Identifying Inaccurate Stories: Leveraging High Knowledge an...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Mohammad Ahmar Khan Pushpendra Kumar Verma Shivangi Ghaldiyal N. V. Balaji G.Arun Francis Swati Bula Patil Department of Management Information System College of Commerce & Business Administration Dhofar University Country Sultanate of Oman School of Computer Science and Applications IIMT University Meerut Department of Computer Applications Invertis University Bareilly Uttar Pradesh India Department of Computer Science Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Electronics and Communication Engineering Karpagam College of Engineering Coimbatore Tamil Nadu India IT Vishwakarma Institute of Technology Pune India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Research on fake news has gained significant traction in a number of fields, We describe how the issue is tackled from a natural language processing standpoint in this research with the aim of developing identify false material in news. Collecting high-quality data, such as examples of false and actual news stories on a diverse range of subjects, is the key obstacle in this field of study. We examine the available before introducing the site as our lab’s gift to the. We provide the whole text of the news that have already been applied based on human evaluation of the articles’ authenticity. In order to clarify the gaps and causes of imbalance in the datasets that are now accessible and to direct ongoing attempts, we also conduct an appearance-based experiment. We urge the public to gather more information and make it accessible for study.

关键词： Deep learning Accuracy Text categorization Training data Big Data Natural language processing Reliability Labeling Fake news

来源：评论

学校读者我要写书评

暂无评论

Realizing Emotional Interactions to Learn User Experience and Guide Energy Optimization for Mobile Architectures 22

Realizing Emotional Interactions to Learn User Experience an...

引用

Proceedings of the 55th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Xueliang Li Zhuobin Shi Junyang Chen Yepang Liu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation and Department of Computer Science and Engineering Southern University of Science and Technology China

ISBN: (纸本)9781665462723

In the age of AI, mobile architectures such as smartphones are still "cold machines"; machines do not feel. If the architecture is able to feel users' feelings and runtime user experience (UX), it will accordingly adapt performance/energy to find the optimal system-operating state that consumes the least energy to satisfy users. In this paper, we will utilize users' facial expressions (FEs) to learn their runtime UX. We know that FEs are the natural and direct way for humans to convey their emotions and feelings. Our study reveals that FEs also reflect UX. Our research for the first time quantifies the link between FEs and UX. Leveraging this link, the architecture will be able to use the front camera to see FEs and feel users' UX. Based on UX, the architecture can appropriately provision computing resources. We propose Vi-energy system to realize the above idea. Our evaluation shows that Vi-energy reduces energy consumption by 52.9% at maximum and secures UX.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OpenGait: Revisiting Gait Recognition Toward Better Practicality

OpenGait: Revisiting Gait Recognition Toward Better Practica...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Chao Fan Junhao Liang Chuanfu Shen Saihui Hou Yongzhen Huang Shiqi Yu Department of Computer Science and Engineering Southern University of Science and Technology Research Institute of Trustworthy Autonomous System Southern University of Science and Technology Department of Industrial and Manufacturing Systems Engineering The University of Hong Kong School of Artificial Intelligence Beijing Normal University WATRIX.AI

Gait recognition is one of the most critical long-distance identification technologies and increasingly gains popularity in both research and industry communities. Despite the significant progress made in indoor datasets, much evidence shows that gait recognition techniques perform poorly in the wild. More importantly, we also find that some conclusions drawn from indoor datasets cannot be generalized to real applications. Therefore, the primary goal of this paper is to present a comprehensive benchmark study for better practicality rather than only a particular model for better performance. To this end, we first develop a flexible and efficient gait recognition codebase named OpenGait. Based on OpenGait, we deeply revisit the recent development of gait recognition by re-conducting the ablative experiments. Encouragingly, we detect some unperfect parts of certain prior woks, as well as new insights. Inspired by these discoveries, we develop a structurally simple, empirically powerful, and practically robust baseline model, Gait-Base. Experimentally, we comprehensively compare Gait-Base with many current gait recognition methods on multiple public datasets, and the results reflect that GaitBase achieves significantly strong performance in most cases regardless of indoor or outdoor situations. Code is available at https://***/ShiqiYu/OpenGait.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hyperdimensional Computing Versus Convolutional Neural Network: Architecture, Performance Analysis, and Hardware Complexity

Hyperdimensional Computing Versus Convolutional Neural Netwo...

引用

International Conference on Microelectronics, ICM

作者： Eman Hassan Meriem Bettayeb Baker Mohammad Yahya Zweiri Hani Saleh Electrical Engineering and Computer Science Department System-on-Chip (SoC) Lab Khalifa University Abu Dhabi UAE Department of Aerospace Engineering and Advanced Research and Innovation Center (ARIC) Khalifa University Abu Dhabi UAE

The interest in brain-inspired computing architectures has been growing, particularly in the context of edge devices with constrained resources for executing cognitive functions. One such approach is hyperdimensional computing (HDC), a novel concept that draws inspiration from the large representation of human neuronal activity. HDC has demonstrated effectiveness in one-dimensional tasks, like text identification and activity recognition, offering advantages in power consumption and response time over convolutional neural networks (CNNs). This paper compares HDC and CNN regarding architecture, accuracy, and hardware complexity, explicitly focusing on image classification tasks. Our findings indicate that CNNs generally outperform HDC in two-dimensional tasks but require significantly more computational resources. In contrast, HDC offers adequate results using just 16% of the data needed for training. Additionally, experiments conducted using a Raspberry Pi 4 show that HDC can enhance inference speed and energy efficiency by approximately 2.5 times relative to CNNs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mfagan: A Compression Framework for Memory-Efficient On-Device Super-Resolution Gan

SSRN

引用

SSRN 2023年

作者： Cheng, Wenlong Ye, Zhiling Kong, Han Zhao, Mingbo Gu, Shuhang Department of Electronic Engineering City University of Hong Kong Hong Kong Tencent Computer System Co. Ltd. Shenzhen China College of Information Science and Technology Donghua University Shanghai China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

Generative adversarial networks (GANs) have promoted remarkable advances in single-image super-resolution (SR) by recovering photo-realistic images. However, high memory consumption of GAN-based SR (usually generators) causes performance degradation and more energy consumption, hindering the deployment of GAN-based SR into resource-constricted mobile devices. In this paper, we propose a novel compression framework Multi-scale Feature Aggregation Net based GAN (MFAGAN) for reducing the memory access cost of the generator. First, to overcome the memory explosion of dense connections, we utilize a memory-efficient multi-scale feature aggregation net as the generator. Second, for faster and more stable training, our method introduces the PatchGAN discriminator. Third, to balance the student discriminator and the compressed generator, we distill both the generator and the discriminator. Finally, we perform a hardware-aware neural architecture search (NAS) to find a specialized SubGenerator for the target mobile phone. Benefiting from these improvements, the proposed MFAGAN achieves up to 8.3× memory saving and 42.9× computation reduction, with only minor visual quality degradation, compared with ESRGAN. Empirical studies also show ∼70 milliseconds latency on Qualcomm Snapdragon 865 chipset. © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Significance of Internet-of-Things Edge and Fog Computing in Education Sector

Significance of Internet-of-Things Edge and Fog Computing in...

引用

Smart Computing and Application (ICSCA), International Conference on

作者： Shams Tabrez Siddiqui Mohammad Rafeek Khan Zeba Khan Nadim Rana Haneef Khan Md Imran Alam Department of Computer Science College of CS & IT Jazan University Jazan Saudi Arabia Department of Computer and Network Engineering College of CS & IT Jazan University Jazan Saudi Arabia Computer and Information System Applied College Jazan University Jazan Saudi Arabia College of Computer Science and Information Technology Jazan University Jazan Saudi Arabia

IoT gadgets include smart lights, ovens, and industrial data-collecting equipment. IDC expects 41.6 billion connected IoT devices to generate 79.4 ZB of data by 2025. Early IoT devices sent data to the cloud for analysis. When sending trillions of gigabytes to the cloud, the data pipeline clogs. Edge computing enables IoT devices to handle data locally instead of sending it to the cloud. Data is processed at the “edge” of your local network, rather than transferred away. Technology's versatility makes it valuable in education. IoT edge computing has different requirements than non-IoT edge computing. IoT devices have limited data processing and storage capabilities, thus processing must occur off the device. The edge offers an environment to manage huge numbers of IoT devices and data. Many functions can be off-loaded to the edge, reducing device cost. In education, IoT edge computing architecture has gained importance due to real-time applications. In order to facilitate the analysis of educational system architecture, this paper seeks to provide an IoT Edge computing framework in the field of education. The framework will identify IoT-related issues and concerns. This study discusses IoT Edge computing in education, identifies limits, and makes recommendations. As well as the paper evaluates IoT Edge computing's performance in educational systems.

关键词： Productivity Cloud computing Privacy systematics Education systems architecture Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Smart Home Light Based Service Oriented Architecture and IoT 1

Smart Home Light Based Service Oriented Architecture and IoT

引用

1st International Conference on Industrial Automation, Smart Grid and its Application, ICIASGA 2020

作者： Irawan, Yuda Chrismondari Yolnasdi Linarta, Ari Muhardi Febriani, Anita Department of Information System STMIK Hang Tuah Pekanbaru Pekanbaru Indonesia Department of Electrical Engineering STT Pekanbaru Pekanbaru Indonesia Department of Information System STMIK Dumai Indonesia Department of Computer Science STMIK Hang Tuah Pekanbaru Pekanbaru Indonesia

The development of technology is very rapid in everyday life, so that it provides benefits for each. One of the advantages is that with technology, users can control electronic equipment which can be done with the smart home application (Smart Home) and from anywhere. This smart home application can help users control household electronic equipment such as lights, air conditioners, TVs, dispensers and others so as to reduce the waste of electricity when users forget to turn off household electronic equipment when traveling outside the house or anywhere. users are located. This research applies the concept of Service Oriented Architecture (SOA) and Internet of Things (IoT) on smart home light by integrating Ras-berry Pi with Python programming, web server (database) with PHP and An-droid programming with Java programming, and in experimental research that will be controlled. is the house light. The results of this research are in the form of a prototype of a home light controller using the IoT concept, web service and the Android SOA Smart home application with 7 buttons to control / monitor lights and this system is integrated with the concept of Service Oriented Architecture which is equipped with a token as system security. Tests have been carried out by controlling house lights remotely using a smartphone via the internet net-work and the results can be controlled properly. © Published under licence by IOP Publishing Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Explainable deep stacking ensemble model for accurate and transparent brain tumor diagnosis

引用

computers in Biology and Medicine 2025年 191卷 110166-110166页

作者： Haque, Rezaul Khan, Mahbub Alam Rahman, Hamdadur Khan, Shakil Siddiqui, Md Ismail Hossain Limon, Zishad Hossain Swapno, S M Masfequier Rahman Appaji, Abhishek Department of Computer Science and Engineering East West University A 2 Jahurul Islam Ave Dhaka1212 Bangladesh Department of Management Information System Pacific State University 3424 Wilshire Blvd. 12th Floor Los Angeles CA90010 United States Department of Management of Information System International American University 3440 Wilshire Blvd STE 1000 Los AngelesCA90010 United States Department of Business Analytics International American University 3440 Wilshire Blvd STE 1000 Los AngelesCA90010 United States Department of Engineering/Industrial Management Westcliff University IrvineCA92614 United States Department of Computer Science Westcliff University IrvineCA92614 United States Department Of Computer Science and Engineering Bangladesh University of Business and Technology Mirpur-2 Dhaka1216 Bangladesh Department of Medical Electronics Engineering B.M.S. College of Engineering Bangalore560019 India Maastricht University University Eye Clinic Maastricht Maastricht Netherlands

Early detection of brain tumors in MRI images is vital for improving treatment results. However, deep learning models face challenges like limited dataset diversity, class imbalance, and insufficient interpretability. Most studies rely on small, single-source datasets and do not combine different feature extraction techniques for better classification. To address these challenges, we propose a robust and explainable stacking ensemble model for multiclass brain tumor classification. To address these challenges, we propose a stacking ensemble model that combines EfficientNetB0, MobileNetV2, GoogleNet, and Multi-level CapsuleNet, using CatBoost as the meta-learner for improved feature aggregation and classification accuracy. This ensemble approach captures complex tumor characteristics while enhancing robustness and interpretability. The proposed model integrates EfficientNetB0, MobileNetV2, GoogleNet, and a Multi-level CapsuleNet within a stacking framework, utilizing CatBoost as the meta-learner to improve feature aggregation and classification accuracy. We created two large MRI datasets by merging data from four sources: BraTS, Msoud, Br35H, and SARTAJ. To tackle class imbalance, we applied Borderline-SMOTE and data augmentation. We also utilized feature extraction methods, along with PCA and Gray Wolf Optimization (GWO). Our model was validated through confidence interval analysis and statistical tests, demonstrating superior performance. Error analysis revealed misclassification trends, and we assessed computational efficiency regarding inference speed and resource usage. The proposed ensemble achieved 97.81% F1 score and 98.75% PR AUC on M1, and 98.32% F1 score with 99.34% PR AUC on M2. Moreover, the model consistently surpassed state-of-the-art CNNs, Vision Transformers, and other ensemble methods in classifying brain tumors across individual four datasets. Finally, we developed a web-based diagnostic tool that enables clinicians to interact with the proposed mo

关键词： Magnetic resonance imaging

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：