检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Conde, Pedro Lopes, Rui L. Premebida, Cristiano Institute os Systems and Robotics Department Of Electrical and Computer Engineering University of Coimbra Portugal Critical Software S.A. Portugal

The proliferation of Deep Neural Networks has resulted in machine learning systems becoming increasingly more present in various real-world applications. Consequently, there is a growing demand for highly reliable models in many domains, making the problem of uncertainty calibration pivotal when considering the future of deep learning. This is especially true when considering object detection systems, that are commonly present in safety-critical applications such as autonomous driving, robotics and medical diagnosis. For this reason, this work presents a novel theoretical and practical framework to evaluate object detection systems in the context of uncertainty calibration. This encompasses a new comprehensive formulation of this concept through distinct formal definitions, and also three novel evaluation metrics derived from such theoretical foundation. The robustness of the proposed uncertainty calibration metrics is shown through a series of representative experiments. Copyright © 2023, The Authors. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficient Crowdsourcing for Video Analytics 40

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficien...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Chen, Yu Zhang, Sheng Zhou, Ziying Wang, Xiaokun Liang, Yu Chen, Ning Yan, Yuting Xiao, Mingjun Wu, Jie Qian, Zhuzhong Xu, Harry Nanjing University State Key Lab. for Novel Software Technology China School of Systems Science Beijing Normal University China School of Computer and Electronic Information School of Artificial Intelligence Nanjing Normal University China School of Computer Science and Technology University of Science and Technology of China China Temple University Center for Networked Computing United States Samueli School of Engineering University of California Computer Science Department Los Angeles United States

ISBN: (纸本)9798350317152

In recent years, many crowdsourcing platforms have emerged, using the resources of recruited workers to perform diverse outsourcing tasks, where the video analytics attracts much attention due to its practical implications. For maximum profits, platforms carefully choose the workers and determine the video analytics configurations to ensure accuracy;meanwhile, workers possess the flexibility to tailor the configurations for their indivi-dual gains, which makes it hard for platforms to optimize their profits considering the platform-worker conflicts. In this paper, we design an incentive mechanism for Multi-leader game-based video Analytics upon CROwdsourcing, named MACRO, to over-come the above situation. Under that mechanism, we first formu-late the utility optimization problems for platforms and workers, respectively. We then propose a dual ascent-based method to op-timally determine the video analytics configurations for a multi-platform game, ensuring Pareto efficiency. Moreover, in the context of a multi-leader game involving platform-worker conflicts, we design an incentive function with its incentive factor update strategy and propose an ADMM-based approach for maximizing incentives that motivate workers to contribute to the platforms' profits. Rigorous proofs demonstrate the linear convergence of the MACRO to the multi-leader Stackelberg equilibrium. Trace-driven experiments show that MACRO improves the Pareto efficiency by 26.3%, outperforming other approaches. © 2024 IEEE.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

Vibrating Particles System Algorithm for Solving Classification Problems

引用

computer systems Science & engineering 2022年第12期43卷 1189-1206页

作者： Mohammad Wedyan Omar Elshaweesh Enas Ramadan Ryan Alturki Department of Autonomous Systems Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan Department of Software Engineering Information Technology CollegeAL-Hussein bin Talal UniversityMa’an71111Jordan Department of Computer Science Prince Abdullah Bin Ghazi Faculty of Communication and Information TechnologyAl-Balqa Applied UniversityAl-Salt19117Jordan Department of Information Science College of Computer and Information SystemsUmm Al-Qura UniversityMakkah21961Saudi Arabia

Big data is a term that refers to a set of data that,due to its largeness or complexity,cannot be stored or processed with one of the usual tools or applications for data management,and it has become a prominent word in recent years for the massive development of *** immediately thereafter,the term“big data mining”emerged,i.e.,mining from big data even as an emerging and interconnected field of *** is an important stage in data mining since it helps people make better decisions in a variety of situations,including scientific endeavors,biomedical research,and industrial *** probabilistic neural network(PNN)is a commonly used and successful method for handling classification and pattern recognition *** this study,the authors proposed to combine the probabilistic neural network(PPN),which is one of the data mining techniques,with the vibrating particles system(VPS),which is one of the metaheuristic algorithms named“VPS-PNN”,to solve classi-fication problems more *** data set is eleven common benchmark medical datasets from the machine-learning library,the suggested method was *** suggested VPS-PNN mechanism outperforms the PNN,biogeography-based optimization,enhanced-water cycle algorithm(E-WCA)and the firefly algorithm(FA)in terms of convergence speed and classification accuracy.

关键词： Vibrating particles system(VPS) probabilistic neural network(PNN) classification problem data mining

来源：评论

学校读者我要写书评

暂无评论

Analysis of converting -circuit into -circuit

引用

EPJ Quantum Technology 2025年第1期12卷 1-14页

作者： Luo, Qing-bin Ding, Lang Yang, Guo-wu Li, Xiao-yu College of Intelligent Systems Science and Engineering Hubei Minzu University Enshi China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Big data research Center & School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

A $\mathfrak{C^{*}}$ -circuit, which was proposed in Asiacypt 2022 by Huang and Sun (Advances in cryptology – ASIACRYPT 2022, pp. 614–644, 2022), can directly perform calculations with the existing quantum states, thereby reducing the use of quantum resources in quantum logic synthesis. We theoretically prove how to convert a $\mathfrak{C^{0}}$ -circuit into the corresponding $\mathfrak{C^{*}}$ -circuit through two lemmas and one theorem. The first lemma proves the interchangeability of CNOT gates and NOT gates by using the equivalence of quantum circuits. The second lemma proves that adding CNOT gates to the front of a quantum circuit whose initial states are all $|0\rangle $ s will not change the output states of the circuit. The theorem is used to describe what kind of $\mathfrak{C^{0}}$ -circuit can be transformed into $\mathfrak{C^{*}}$ -circuit, and the correctness of this transformation is proved. Our work will provide a theoretical basis for converting $\mathfrak{C^{0}}$ -circuit to $\mathfrak{C^{*}}$ -circuit. Then applying the theoretical analysis results to the multiplication over $\text{GF}(2^{8})$ , the constructed quantum circuit needs 27 Toffoli gates and 118 CNOT gates, which is 15 fewer Toffoli gates and 43 CNOT gates than the current best result. This shows that the method of constructing quantum circuits by using the conversion of $\mathfrak{C^{0}}$ -circuit to $\mathfrak{C^{*}}$ -circuit is very efficient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Soft Computing Based Metaheuristic Algorithms for Resource Management in Edge Computing Environment

引用

computers, Materials & Continua 2022年第9期72卷 5233-5250页

作者： Nawaf Alhebaishi Abdulrhman M.Alshareef Tawfiq Hasanin Raed Alsini Gyanendra Prasad Joshi Seongsoo Cho Doo Ill Chul Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Computer Science and Engineering Sejong UniversitySeoulKorea School of Software Soongsil UniversitySeoul06978Korea Artificial Intelligence Education Hankuk University of Foreign StudiesDongdaemun-guSeoul02450Korea

In recent times,internet of things(IoT)applications on the cloud might not be the effective solution for every IoT scenario,particularly for time sensitive applications.A significant alternative to use is edge computing that resolves the problem of requiring high bandwidth by end *** computing is considered a method of forwarding the processing and communication resources in the cloud towards the *** of the considerations of the edge computing environment is resource management that involves resource scheduling,load balancing,task scheduling,and quality of service(QoS)to accomplish improved *** this motivation,this paper presents new soft computing based metaheuristic algorithms for resource scheduling(RS)in the edge computing *** SCBMARS model involves the hybridization of the Group Teaching Optimization Algorithm(GTOA)with rat swarm optimizer(RSO)algorithm for optimal resource *** goal of the SCBMA-RS model is to identify and allocate resources to every incoming user request in such a way,that the client’s necessities are satisfied with the minimum number of possible resources and optimal energy *** problem is formulated based on the availability of VMs,task characteristics,and queue *** integration of GTOA and RSO algorithms assist to improve the allocation of resources among VMs in the data *** experimental validation,a comprehensive set of simulations were performed using the CloudSim *** experimental results showcased the superior performance of the SCBMA-RS model interms of different measures.

关键词： Resource scheduling edge computing soft computing fitness function virtual machines

来源：评论

学校读者我要写书评

暂无评论

Reliability and Timeliness of Servicing Requests in Infocommunication systems, Taking into Account the Physical and Information Recovery of Redundant Storage Devices 6

Reliability and Timeliness of Servicing Requests in Infocomm...

引用

6th International Scientific Conference on Information, Control, and Communication Technologies, ICCT 2022

作者： Bogatyrev, Vladimir A. Bogatyrev, Stanislav V. Bogatyrev, Anatoly V. Saint-Petersburg State University of Aerospace Instrumentation Department Information Systems Security Saint Petersburg Russia Itmo University Faculty of Software Engineering and Computer Systems Saint Petersburg Russia Yadro Cloud Storage Development Center Saint Petersburg Russia

ISBN: (数字)9781665493673

ISBN: (纸本)9781665493673

Markov models of reliability of fault-tolerant computer systems are proposed, taking into account two stages of recovery of redundant memory devices. At the first stage, the physical recovery of memory devices is implemented, and at the second, the informational one consists in entering the data necessary to perform the required functions. Memory redundancy is carried out to increase the stability of the system to the loss of unique data generated during the operation of the system. Data replication is implemented in all functional memory devices. Information recovery is carried out using replicas of data stored in working memory devices. The model takes into account the criticality of the system to the timeliness of calculations in real time and to the impossibility of restoring information after multiple memory failures, leading to the loss of all stored replicas of unique data. The system readiness coefficient and the probability of its transition to a non-recoverable state are determined. The readiness of the system for the timely execution of requests is evaluated, taking into account the influence of the shares of the distribution of the performance of the computer allocated for the maintenance of requests and for the entry of information into memory after its physical recovery. © 2022 IEEE.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Predicting software Functional Size Using Natural Language Processing: An Exploratory Case Study

Predicting Software Functional Size Using Natural Language P...

引用

Euromicro Conference on software engineering and Advanced Applications (SEAA)

作者： Hüseyin Ünlü Samet Tenekeci Can Çiftçi İbrahim Baran Oral Tunahan Atalay Tuna Hacaloğlu Burcu Musaoğlu Onur DemirǶrs Department of Computer Engineering Izmir Institute of Technology Izmir Turkiye Bilgi Grubu Izmir Turkiye Department of Information Systems Engineering Atilim University Ankara Turkiye Department of Software and IT Engineering Ecole de Technologie Superieure Montreal Canada Siskon Software & Automation Izmir Turkiye

ISBN: (数字)9798350380262

ISBN: (纸本)9798350380279

software Size Measurement (SSM) plays an essential role in software project management as it enables the acquisition of software size, which is the primary input for development effort and schedule estimation. However, many small and medium-sized companies cannot perform objective SSM and software Effort Estimation (SEE) due to the lack of resources and an expert workforce. This results in inadequate estimates and projects exceeding the planned time and budget. Therefore, organizations need to perform objective SSM and SEE using minimal resources without an expert workforce. In this research, we conducted an exploratory case study to predict the functional size of software project requirements using state-of-the-art large language models (LLMs). For this aim, we fine-tuned BERT and BERT_SE with a set of user stories and their respective functional size in COSMIC Function Points (CFP). We gathered the user stories included in different project requirement documents. In total size prediction, we achieved 72.8% accuracy with BERT and 74.4% accuracy with BERT_SE. In data movement-based size prediction, we achieved 87.5% average accuracy with BERT and 88.1% average accuracy with BERT_SE. Although we use relatively small datasets in model training, these results are promising and hold significant value as they demonstrate the practical utility of language models in SSM.

关键词： Training Schedules Accuracy Estimation Project management Companies Predictive models Size measurement software Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Improving Fake News Detection with a Mixture of Experts: Leveraging Sentiment Analysis and Sarcasm Detection as Core Expert Models

Improving Fake News Detection with a Mixture of Experts: Lev...

引用

Advancements in Computing (ICAC), International Conference on

作者： Tharindu Gunasekara Disira Thihan Sansika Kodithuwakku Dinuka Dissanayake Harinda Fernando Samitha Vidhanaarachchi Archchana Sindhujan dept. of Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka dept. of Computer Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka dept. of Computer Science and Electronic Engineering University of Surrey United Kingdom

ISBN: (数字)9798331517878

ISBN: (纸本)9798331517885

Fake news continues to proliferate, posing an increasing threat to public discourse. The paper proposes a framework of a Mixture of Experts, Sentiment Analysis, and Sarcasm Detection experts for improved fake news detection. This approach captures the emotional cues in the text through a Sentiment Analysis expert, which is based on bidirectional encoder representations from Transformers (BERT) models with sentiment vectors generated using SentiWordNet and Integrated Gradients. It combines a sarcasm detection expert based on BERT, recognizing sarcasm and its type to help classify fake news. By fusing these experts through a Mixture of Experts gateway, subtle linguistic cues often found in fake news are more effectively analyzed, leading to improved accuracy in detecting misinformation. Experimental results are presented as 96% for the Sarcasm expert with the BERT base model and 83% for the Sentiment Analysis expert with the distilled version of the BERT (DistilBERT) base model, proving the effectiveness of the proposed approach in beating traditional methods.

关键词： Sentiment analysis Analytical models Accuracy Bidirectional control Logic gates Linguistics Transformers Encoding Vectors Fake news

来源：评论

学校读者我要写书评

暂无评论

Blood Cell Classification and Counting in Hematology through Deep Learning

Blood Cell Classification and Counting in Hematology through...

引用

Sustainable Expert systems (ICSES), International Conference on

作者： P. Ananthi K Nirmala Devi T. E. Ramya P. Shanmugapriya T. Aradhya Department of Computer Technology Kongu Engineering College Perundurai Erode Tamil Nadu Department of Computer Applications Madanapalle Institute of Technology & Science M.Sc Software Systems Kongu Engineering College Perundurai Erode Tamil Nadu

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Medical diagnosis is one of the areas that has been greatly influenced by the progress of computer vision technologies. This study presents a unique approach for the detection and counting of blood cells in hematology: You Only Look One algorithm version 7 (YOLOv7). YOLO is designed for real-time object detection, making it ideal for applications such as blood vessel detection where speed is critical. The architecture allows the model to process images faster than other recognition models, such as R-CNN or SSD, which is very important for situations that require fast results, such as analysis automatic blood at clinical sites. The purpose of the proposed method is to overcome the shortcomings of conventional methods and to accurately and quickly identify blood cells in mechanical images. The YOLOv7 model has been utilizedbecause it can detect objects in real-time with highprecision and speed. The methodology for bloodcell counting involves the use of YOLOv7 togenerate bounding boxes around each detectedblood cell in an image, where the count of these bounding boxes directly corresponds to the number of cells. This advancement in hematology not onlyimproves blood cell analysis efficiency but also expedites the process of diagnosing and planningtreatment in various medical situations. This paper details how YOLOv7 was modified and adjusted to meet the specific requirements of hematologicalimage analysis, including training models, preparing datasets, and evaluating performance. The study also addresses the potential impact of this technology on clinical workflows, highlightinghow it might help medical practitioners make decisions more quickly and intelligently. Hematology analysis systems including YOLOv7 are able to improve laboratory diagnostics and help patients by providing better care and results. This workconcludes by demonstrating the revolutionary potential of YOLOv7 in blood cell identificationand counting in hematology, paving the way for accurate and better

关键词： Analytical models Accuracy Computational modeling Cells (biology) Real-time systems Reliability Object recognition Medical diagnosis Blood Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Multi-Dataset Multi-Task Learning for COVID-19 Prognosis

arXiv

引用

arXiv 2024年

作者： Ruffini, Filippo Tronchin, Lorenzo Wu, Zhuoru Chen, Wenting Soda, Paolo Shen, Linlin Guarrasi, Valerio Unit of Computer Systems & Bioinformatics Department of Engineering Università Campus Bio-Medico di Roma Rome Italy College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Hong Kong

In the fight against the COVID-19 pandemic, leveraging artificial intelligence to predict disease outcomes from chest radiographic images represents a significant scientific aim. The challenge, however, lies in the scarcity of large, labeled datasets with compatible tasks for training deep learning models without leading to overfitting. Addressing this issue, we introduce a novel multi-dataset multi-task training framework that predicts COVID-19 prognostic outcomes from chest X-rays (CXR) by integrating correlated datasets from disparate sources, distant from conventional multi-task learning approaches, which rely on datasets with multiple and correlated labeling schemes. Our framework hypothesizes that assessing severity scores enhances the model's ability to classify prognostic severity groups, thereby improving its robustness and predictive power. The proposed architecture comprises a deep convolutional network that receives inputs from two publicly available CXR datasets, AIforCOVID for severity prognostic prediction and BRIXIA for severity score assessment, and branches into task-specific fully connected output networks. Moreover, we propose a multi-task loss function, incorporating an indicator function, to exploit multi-dataset integration. The effectiveness and robustness of the proposed approach are demonstrated through significant performance improvements in prognosis classification tasks across 18 different convolutional neural network backbones in different evaluation strategies. This improvement is evident over single-task baselines and standard transfer learning strategies, supported by extensive statistical analysis, showing great application potential. © 2024, CC BY-NC-SA.

关键词： COVID-19

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：