检索结果-内蒙古大学图书馆

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Majeed, Omar Kashif Ul Abideen, Zain Arshad, Usama Ali, Raja Hashim Habib, Abdullah Mustafa, Rafay 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

The fashion industry, with its myriad choices, often overwhelms consumers. Addressing this, AdaptiveCloset introduces a groundbreaking approach to tailoring clothing suggestions by harnessing the power of reinforcement learning (RL). Unlike conventional AI methodologies in a fashion that merely suggests based on past preferences, our system dynamically ad-justs using realtime user feedback, ensuring that recommendations remain relevant and personalized. Historically, AI's fusion into the fashion realm has witnessed multiple methodologies but conspicuously lacked the RL perspective. Our research stands at this juncture, aiming to redefine online shopping experiences. Through AdaptiveCloset, we envisage a scenario where online shoppers not only receive personalized recommendations but also feel a sense of involvement, thanks to the system's feedback-oriented adaptability. This responsiveness not only augments user engagement but provides actionable intelligence for businesses, bridging the gap between consumer desires and market offerings. In this study, our focus was to ensure the robustness and adaptability of the RL environment, positioning it as a potent tool for enhancing e-commerce interactions, optimizing sales strategies, and fortifying customer loyalty. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation as a Market: A Case Study on Multi-Server Multi-Model Federated Learning

Resource Allocation as a Market: A Case Study on Multi-Serve...

引用

Annual Conference on Wireless On Demand Network systems and Services (WONS)

作者： Maria Diamanti Aisha B Rahman Panagiotis Charatsaris Eirini Eleni Tsiropoulou Symeon Papavassiliou Institute of Communication and Computer Systems School of Electrical and Computer Engineering National Technical University of Athens Athens Greece Dept. of Electrical and Computer Engineering University of New Mexico Albuquerque NM USA

ISBN: (数字)9783903176713

ISBN: (纸本)9798331522025

6G networks envision a seamless integration of data and AI into their core operations, marking a new era where distributed client devices actively engage in intelligent processes, supported by a diverse ecosystem of AI service providers. This shift necessitates approaching traditional resource allocation problems from a market perspective, transparently reflecting the gains and losses of clients and providers within the ecosystem. In this paper, we use a multi-server, multi-model Federated Learning (FL) network as a case study to propose a market-based resource allocation framework. The framework models the joint problem of client resource allocation and pricing as a Fisher market, where servers compete to attract clients with private data and local computing resources for distributed model training. The joint problem is formulated as a convex program, aiming to maximize the total server utility related to their model’s accuracy, while incorporating clients’ total computing resource constraints and servers’ budget constraints. An analytical solution to the convex program is derived concluding the so-called Market Equilibrium (ME) point, where market clearance is achieved. The effectiveness of the proposed market-based resource allocation framework is validated through comparisons with established resource allocation and sharing schemes from the literature.

关键词： Federated learning Computational modeling Biological system modeling Ecosystems Distributed databases Pricing Data models Resource management Servers Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Tensor Low-Rank Approximation for Value Functions in Multi-Task Reinforcement Learning

A Tensor Low-Rank Approximation for Value Functions in Multi...

引用

Asilomar Conference on Signals, systems & computers

作者： Sergio Rozada Santiago Paternain Juan Andrés Bazerque Antonio G. Marques Dept. of Signal Theory and Communications King Juan Carlos University Madrid Spain Dept. of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY USA Dept. of Electrical and Computer Engineering University of Pittsburgh Pittsburgh PA USA

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

In pursuit of reinforcement learning systems that could train in physical environments, we investigate multi-task approaches as a means to alleviate the need for massive data acquisition. In a tabular scenario where the Q-functions are collected across tasks, we model our learning problem as optimizing a higher order tensor structure. Recognizing that close-related tasks may require similar actions, our proposed method imposes a low-rank condition on this aggregated Q-tensor. The rationale behind this approach to multi-task learning is that the low-rank structure enforces the notion of similarity, without the need to explicitly prescribe which tasks are similar, but inferring this information from a reduced amount of data simultaneously with the stochastic optimization of the Q-tensor. The efficiency of our low-rank tensor approach to multi-task learning is demonstrated in two numerical experiments, first in a benchmark environment formed by a collection of inverted pendulums, and then into a practical scenario involving multiple wireless communication devices.

关键词： Wireless communication Training Performance evaluation Tensors Stochastic processes Reinforcement learning Multitasking Throughput Parametric statistics Optimization

来源：评论

学校读者我要写书评

暂无评论

Predicting Analysis of the Multi-Sensor Signals in Terms of Time Series

Predicting Analysis of the Multi-Sensor Signals in Terms of ...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Sergei Zuev Petr Kabalyants Dept. of computer software and automated systems Belgorod State Technological University named after V. G. Shoukhov Belgorod Russia

This study is aimed to present a new way to predict multi-sensor signals values based on the given values registered before. The method is based on the generalised serialisation method, proposed by the author earlier, and autoregression with adjustable window width. The given signals have been received as a sequence of values related to a random instances of measurements. However there exist some patterns that imply the values to be not random in fact. It is natural in this proposition to consider all the signals came from the object to be predictable up to some precision due to the pattern for every signal exists. It is shown in the paper how to make such unification of the signals to receive the time series; there are various methods of prediction for the time series, and autoregression is chosen for this study; the generalised serialisation method allows to transform the value predicted by autoregression to the multi-values needed for prediction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Validation of Design Metrics in Machine Learning for Depression Detection

Evaluation and Validation of Design Metrics in Machine Learn...

引用

International Conference on Emerging Technologies, ICET

作者： Sahar Ajmal Muhammad Usman Abqa Javed Dept. of Software Engineering National University of Computer and Emerging Sciences Chiniot-Faisalabad Pakistan Dept. of Computer Science National University of Computer and Emerging Sciences Chiniot-Faisalabad Pakistan Dept. of Computer Science Univ. of Engineering and Technology Lahore Pakistan

Depression is a medical syndrome that is often neglected and considered not as significant as physical illness due to lack of awareness and knowledge, but it should be treated in early stages to avoid extreme cases such as suicide. Therefore, Machine Learning Algorithms (MLA) are used to detect depression primitively to avoid extreme hazards. In-ternational Organization for Standardization (ISO) standards are essential for designing metrics in MLA as they ensure global consistency, quality assurance, and objective benchmark, enhancing credibility and reliability of the model. Although there is no proper standard design level quality metric is defined for MLA. Therefore, in this study, ISO 9126 standard is used to make as a quality standard considering functionality parameter of MLA design. These metrics are used to evaluate at the design level of MLA such as evaluation of dataset, preprocessing, MLA, and results. We have provide comparative analysis of MLA with partial functionality compliance with full ISO functionality conformance. In this study, MLA with ISO have significance compliance which is promising, where the raw data added to MLA to get the output and or the other hand all the steps are performed. The results clearly show that proposed model of MLA design metrics are out-performed provides 28% better results in terms of evaluations. Furthermore, the proposed design quality metrics can be used as the standard for the MLA domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Hardware Implementation of Seizure Detector Using Machine Learning

Efficient Hardware Implementation of Seizure Detector Using ...

引用

International Conference on Microelectronics, ICM

作者： Mariam K. El-Tanbadawy Mohammed A. Megeed Salem Mohamed A. Abd ElGhany Electronics Engineering Dept. German University in Cairo Egypt Computer Engineering Dept. German University in Cairo Egypt Integrated Electronic Systems Lab TU Darmstadt Germany

ISBN: (数字)9798350379396

ISBN: (纸本)9798350379402

In the past few decades, Seizure Detection has been a vital cornerstone in biomedical research. Both hardware and software implementations have been explored to improve algorithms, detection performance and resources. In this paper, three handcrafted features composed of Coastline Function, Hurst Exponent and Fractal Dimension are used as training data for supervised learning models to build an efficient and sensitive seizure detector. Random Forest classifier exhibits the best accuracy at 98%. Hardware efficiency, too, is exploited through a modified Feature Extractor that combines the aforementioned features. The features are adjusted to reduce their hardware resources on Virtex-7 FPGA. The area utilization is improved by 10%, power utilization is improved by 20% and latency decreased by 32%.

关键词： Training Coastlines Accuracy Training data Detectors Feature extraction Hardware software Fractals Random forests

来源：评论

学校读者我要写书评

暂无评论

Posture Recognition-Based Robot Control Using Media Pipe Pose

Posture Recognition-Based Robot Control Using Media Pipe Pos...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Jong Woo Kim Seo Yeong Mun BoJeong Park Younglim Choi Hyunseok Kim dept. of Electronic Engineering Dong-A University Busan South Korea dept.of Mechanical Engineering Dong-A University Busan South Korea dept. of Software Innovation Center Dong-A University Busan South Korea dept. of Computer Engineering Dong-A University Busan South Korea

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

This study proposed a body movement-based system for efficiently controlling robots in large indoor environments. Traditional hand gesture recognition systems experience significant accuracy loss in large indoor spaces, particularly as the distance between the user and the camera grows. To address this issue, clear and large body movements were used as control signals instead of hand movements. For example, participants could give commands to the robot by raising both hands or lifting one hand in a specific direction. The system utilized MediaPipe Pose to track the user's posture in real time and communicated commands from the server to the robot via TCP/IP socket communication. This structure ensured stable data transmission, enabling smooth robot control even in expansive spaces. Consequently, this research demonstrated the feasibility of effective robot control in large indoor areas, such as screen golf courses, and suggested the potential for system expansion in various indoor environments.

关键词： Hands Tracking Sockets Robot control Robot vision systems TCPIP Aerospace electronics Real-time systems Indoor environment Servers

来源：评论

学校读者我要写书评

暂无评论

Advancements in Dental Diagnostics: YOLOv3-Powered Machine Learning for Automated Teeth Problem Detection

Advancements in Dental Diagnostics: YOLOv3-Powered Machine L...

引用

Information Technology (ACIT)

作者： Suhail Odeh Anas Samara Nicola Zreineh Seif Obeid Maen Ibrieghieth Mahmoud Obaid Software Engineering Dept. Bethlehem University Palestine Computer System Engineering Arab American University Jenin Palestine

This paper presents a rigorous investigation into the application of state-of-the-art machine learning techniques for the automated detection of dental issues, utilizing the YOLOv3 Algorithm, a cutting-edge one-stage object detection method. The study encompasses the meticulous annotation and utilization of a carefully curated dataset featuring 126 panoramic X-ray images, illustrating a diverse range of dental conditions. Among these conditions, the primary emphasis is placed on the precise detection of six specific dental problems. Employing advanced computer vision methodologies, the model demonstrates exceptional accuracy in the identification and precise localization of these targeted dental issues. The implications of these findings are profound for the field of dental healthcare, as the automated detection of dental problems holds the potential to significantly enhance the diagnostic and treatment planning capabilities of dental professionals. The results presented in this research represent a notable stride in the ongoing evolution of machine learning and underscore its capacity to revolutionize the landscape of dental diagnostics, ultimately contributing to the advancement of oral health management and patient care.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-Based Framework for Data Exchange to Enhance Global Healthcare

引用

Procedia computer Science 2024年 241卷 570-575页

作者： Ammerha Naz Muhammad Ali Sehrish Munawar Cheema Ivan Miguel Pires Dept. of Computer Science University of Sialkot Sialkot Punjab Dept. of Software Engineering Superior University Lahore Pakistan Dept. of Computer Science University of Management and Technology Lahore Pakistan Instituto de Telecomunicações Escola Superior de Tecnologia e Gestão de Águeda Universidade de Aveiro Águeda Portugal

Healthcare is a global pillar, with a surge in the adoption of information technology, particularly in hospital information systems (HIS). However, global protocols are needed to meet the growing demand for data interchange, practical implementations for sharing healthcare data among facilities, and a pressing need for processing and storage infrastructure to handle the escalating volume of healthcare data. This study proposes a solution for efficient data transmission using electronic health records (EHR) and Platform-as-a-Service (PaaS) to leverage cloud computing resources. This framework's architecture boasts robustness and adaptability, providing all registered software programs access to data interchange services. Through a comprehensive examination of the framework's structure, the essay also explores the most effective data-sharing methods. It identifies the healthcare system's optimal EHR data model. According to multiple healthcare experts, the operational building of this framework is expected to catalyze the growth of healthcare institutions both nationally and within specific industries.

关键词： Healthcare Hospital information systems (HIS) Electronic health records (EHRs) Cloud computing. Data transmission

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Digital Forensic Data for Unbreakable Trust and Security

Blockchain Based Digital Forensic Data for Unbreakable Trust...

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： M. Imrankhan M. Viji R. Sathishkumar T. Gnanaprakash R. Karthik Roshan G. Saravanan Dept. of CSE Manakula Vinayagar Institute of Technology Puducherry Dept. of Computer Science and Business Systems Sri Manakula Vinayagar Engineering College Puducherry

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510039

This can be one of the most magnificent advantages realized from applying blockchain technology in a forensic investigation context, namely, a transformative approach to address challenges embedded within legal and criminal justice systems. For example, smart contracts, being self-executing agreements with the automated inclusion of predefined rules, may even automate and secure the process of tracking evidence, managing chain of custody, and access control. This smart contract will ensure that forensic operations are transparent and of sound integrity. Every transaction and action performed on the blockchain is recorded there, instantaneously bringing down tampering to the lowest possibility and any chance for human mistakes. Regarding decentralized nature and cryptography-based security combined with immutability, blockchain is a technology known to have safeguards over sensitive data. Once recorded on the blockchain, the information thereupon becomes completely un-changeable, assuring the reliability and authenticity of evidence. This will be especially important in the management of an unforgeable chain of custody and in ensuring that forensic evidence remains unchanged and can be relied on with integrity throughout the court process.[6] Critical data can then be maintained tamper-proof for management and storage by developing Ethereum-based smart contracts on Remix IDE using Solidity.[15]Each transaction will be time-stamped and safely logged on the Ethereum blockchain, thus developing an unchallenged ledger that makes any investigation that much more trustworthy. In a nutshell, the application of blockchain in forensic activities builds greater control and efficiencies, reduces possible errors and conflicts, and provides transparency, integrity, and an unchangeable, permanent record for forensic processes. The invention thereby significantly upgrades the general integrity and confidence in legal and criminal justice inquiries.

关键词： Technological innovation Forensics Smart contracts Digital forensics Process control Market research Blockchains Reliability Protection Standards

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：