检索结果-内蒙古大学图书馆

3rd International Conference on Innovations in Computing Research, ICR 2024

作者： Mariettou, Savina Koutsojannis, Constantinos Triantafillou, Vassilios Electrical and Computer Engineering Department University of Peloponnese Patras Greece Health Physics and Computational Intelligence Lab Physiotherapy Department School of Health Rehabilitation Sciences University of Patras Patras Greece Network Technologies and Digital Transformation Lab Electrical and Computer Engineering Department University of Peloponnese Patras Greece

ISBN: (纸本)9783031655210

Machine learning has gained popularity in medical fields due to the increasing availability of health data and the improvement of machine learning algorithms. It can be used to create predictive models that diagnose diseases, predict disease progression, tailor treatment to individual patient needs, and improve the functioning of medical systems. The right use of data can have a positive impact on improving the quality of patient care, reducing healthcare costs, and creating tailored and effective medical approaches. The healthcare sector benefits greatly from the accurate interpretation of medical data as it contributes to the early prediction of diseases in patients. Early detection of a disease can help control the symptoms and provide the correct treatment. In our work, we analyzed actual measurements from the Framingham Heart Study and we created a medical database with 78001 records. Our ultimate goal is to develop an expert Artificial Intelligence system and an Artificial Neural Network that can predict the development of coronary heart disease by employing intelligent knowledge-mining algorithms. We have created two intelligent systems that predict the progression of coronary heart disease using machine learning algorithms such as Random Forest, Decision Trees and Neural Networks. In our experimental analysis, the Decision Tree and Neural Network achieved an accuracy of 90.08% and 84.56% respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated Hematology: Blood Cells Detection and Classification Using Deep Learning Algorithms 17

Automated Hematology: Blood Cells Detection and Classificati...

引用

17th International Conference on Open Source Systems and Technologies, ICOSST 2023

作者： Shah, Aqib Raza Mahboob, Tahira Yaseen, Hira Mehmood, Muhammad Qasim of the Punjab MicroNano Lab Department of Electrical Engineering Lahore Pakistan of the Punjab Department of Computer and Software Engineering Lahore Pakistan

ISBN: (纸本)9798350381320

A comprehensive assessment of blood cell components serves as a pivotal step in recognizing specific health issues in individuals. The analysis of life-Threatening conditions like myeloma and thrombocytopenia underscores the quantification of platelets, erythrocytes (RBCs), and leukocytes (WBCs). Conventional methods, comprising automated analyzers, and manual counting were frequently employed, but they are laborious, lengthy, costly, and require the skills of numerous medical professionals. To mitigate the aforementioned slow and expensive techniques, this study utilizes a deep learning-driven system for object recognition and categorization, employing the You Only Look Once (YOLO) algorithm to count blood cells. The Tiny YOLO model was trained on the BCCD dataset, utilizing a customized architecture designed specifically for detecting the different components of blood cells. Following this, a Convolutional Neural Network (CNN) was utilized to classify the identified WBCs. © 2023 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Multi-State-Space Reasoning Reinforcement Learning for Long-Horizon RFID-Based Robotic Searching and Planning Tasks

引用

Journal of Communications and Information Networks 2022年第3期7卷 239-251页

作者： Zhitao Yu Jian Zhang Shiwen Mao Senthilkumar C G Periaswamy Justin Patton Department of Electrical and Computer Engineering Auburn UniversityAuburnAL 36849-5201USA Department of Electrical and Computer Engineering Kennesaw State UniversityKennesawGA 30144USA RFID Lab at Auburn University AuburnAL 36849USA

In recent years,reinforcement learning(RL)has shown high potential for robotic ***,RL heavily relies on the reward function,and the agent merely follows the policy to maximize rewards but lacks reasoning *** a result,RL may not be suitable for long-horizon robotic *** this paper,we propose a novel learning framework,called multiple state spaces reasoning reinforcement learning(SRRL),to endow the agent with the primary reasoning ***,we abstract the implicit and latent links between multiple state ***,we embed historical observations through a long short-term memory(LSTM)network to preserve long-term memories and *** proposed SRRL’s ability of abstraction and long-term memory enables agents to execute long-horizon robotic searching and planning tasks more quickly and reasonably by exploiting the correlation between radio frequency identification(RFID)sensing properties and the environment occupation *** experimentally validate the efficacy of SRRL in a visual game-based simulation *** methodology outperforms three state-of-the-art baseline schemes by significant margins.

关键词： reinforcement learning multiple state spaces abstract reasoning long-horizon robotic task

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Approach to Target Capture in the Presence of a Defender

A Reinforcement Learning Approach to Target Capture in the P...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Bandela, Suraj Rao Sinha, Abhinav Cao, Yongcan Department of Electrical and Computer Engineering The University of Texas at San Antonio San AntonioTX78249 United States Lab Department of Aerospace Engineering and Engineering Mechanics University of Cincinnati CincinnatiOH45221 United States Department of Electrical and Computer Engineering The University of Texas at San Antonio San AntonioTX78249 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This paper presents a novel paradigm for solving a complex pursuit scenario involving a pursuer, an evader (which is a stationary target), and a reactive defender by leveraging reinforcement learning and data-driven methodologies. The pursuit scenario entails a three body engagement under bounded control conditions, where the pursuer and the defender possess equally matched attributes regarding speed, maneuverability, and turn constraints. The goal is to develop a bi-objective guidance law that enables the pursuer to successfully capture the evader (or stationary target) while effectively avoiding the defender who is trying to safeguard the target and reacting to the pursuer’s actions. We establish that the analytical computation of a feasible strategy for the pursuer that ensures target capture in the presence of an equally capable defender may exhibit NP-hard characteristics and could be intractable. To overcome this challenge, we introduce a multifaceted reward framework based solely on relative measurements that serve as the foundation for the pursuer (the deep reinforcement learning agent) to learn an adaptive guidance strategy against the evader-defender team. Remarkably, our proposed approach operates independently of prior knowledge of the defender’s strategy. We empirically validate the proposed methodology’s effectiveness and versatility through extensive simulations encompassing diverse engagement scenarios and defender guidance laws. Our results indicate the effectiveness of the proposed approach across various engagement dynamics, highlighting its potential utility in complex pursuit-evasion scenarios characterized by distinct agent behaviors. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing 24

LLMParser: An Exploratory Study on Using Large Language Mode...

引用

44th ACM/IEEE International Conference on Software engineering, ICSE 2024

作者： Ma, Zeyang Chen, An Ran Kim, Dong Jae Chen, Tse-Hsun Peter Wang, Shaowei Lab MontrealQC Canada University of Alberta Electrical and Computer Engineering Department EdmontonAB Canada University of Manitoba Department of Computer Science WinnipegMB Canada

ISBN: (纸本)9798400702174

Logs are important in modern software development with runtime information. Log parsing is the first step in many log-based analyses, that involve extracting structured information from unstructured log data. Traditional log parsers face challenges in accurately parsing logs due to the diversity of log formats, which directly impacts the performance of downstream log-analysis tasks. In this paper, we explore the potential of using Large Language Models (LLMs) for log parsing and propose LLMParser, an LLM-based log parser based on generative LLMs and few-shot tuning. We leverage four LLMs, Flan-T5-small, Flan-T5-base, LLaMA-7B, and ChatGLM-6B in LLMParsers. Our evaluation of 16 open-source systems shows that LLMParser achieves statistically significantly higher parsing accuracy than state-of-the-art parsers (a 96% average parsing accuracy). We further conduct a comprehensive empirical analysis on the effect of training size, model size, and pre-training LLM on log parsing accuracy. We find that smaller LLMs may be more effective than more complex LLMs;for instance where Flan-T5-base achieves comparable results as LLaMA-7B with a shorter inference time. We also find that using LLMs pre-trained using logs from other systems does not always improve parsing accuracy. While using pre-trained Flan-T5-base shows an improvement in accuracy, pre-trained LLaMA results in a decrease (decrease by almost 55% in group accuracy). In short, our study provides empirical evidence for using LLMs for log parsing and highlights the limitations and future research direction of LLM-based log parsers. © 2024 ACM.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Bifurcation Analysis under Various Modulation Techniques in PWM-Controlled DC-DC Converters 50

Bifurcation Analysis under Various Modulation Techniques in ...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Ghaderi, Mohammad Hassan Fard, Milad Bahrami Rashidirad, Nasim Fahimi, Babak Balsara, Poras T. Lab Department of Electrical and Computer Engineering University of Texas at Dallas RichardsonTX United States VarennesQC Canada

ISBN: (纸本)9781665464543

The type of carrier signal waveform plays a pivotal role in the dynamic response of the PWM-controlled DC-DC converters. To fully understand the nonlinear behavior of DC-DC converters, this paper aims to dissect the bifurcation process in a PWM-controlled buck converter under various modulations. To this end, various carrier signal waveforms, including single-edge modulation, symmetrical and asymmetrical dual-edge modulations, and various phase-shifted PWMs are considered. Next, using discrete-time modeling, the dynamic analysis of the system at various phase shifts is performed. Inspection of the bifurcation diagram and eigenvalue trajectories, obtained by shifting the gate signal within the switching period, reveals that the converter experiences period-1, period-2, and period-4 orbits within one switching period. The results of this analysis are validated through simulation studies and experiments. © 2024 IEEE.

关键词： Bifurcation carrier signal modulation signal phase shift pulse-width modulation-controlled (PWM-controlled) DC-DC converter Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Explorative Study on Motor Interference During Synchronous Human and Robot Arm Movements Under Varied Presence of a Robot Head

Explorative Study on Motor Interference During Synchronous H...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Kaya, Mertcan Kuhnlenz, Kolja Coburg University of Applied Sciences and Arts Robotics Research Lab Department of Electrical Engineering and Computer Science Coburg Germany

ISBN: (纸本)9781665481090

This paper investigates the influence of a static robot head on deviations of human hand movements from task direction (motor interference) during simultaneous human and robot arm movements using a collaborative robot arm. Synchronous vertical and horizontal human and robot arm movements are conducted in all combinations (within-subjects factors direction and congruency). The presence of the head (head/ no head) is varied as a between-subjects factor. In this first step, only its motionless presence is deliberately focused at, in order to exclude contributions by eye- or head-movement behavior or facial expressions being difficult variables to generalize from. Participants' hands are tracked optically marker-based and deviations from task-related vertical, respectively, horizontal movements are evaluated. In contrast to expectations, results do not show a significant impact of the robot head on motor interference. Thus, there is evidence, that appearance might not be an activating factor for motor interference in HRI. © 2024 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence Enabled Student Performance Estimation in the Age of COVID-19

引用

SN computer Science 2022年第1期3卷 41页

作者： Bansal, Vipul Buckchash, Himanshu Raman, Balasubramanian Machine Vision Lab Department of Computer Science and Engineering Indian Institute of Technology Roorkee India

The sudden advent of COVID-19 pandemic left educational institutions in a difficult situation for the semester evaluation of students;especially where the online participation was difficult for the students. Such a situation may also happen during a similar disaster in the future. Through this work, we want to study the question: can the deep learning methods be leveraged to predict student grades based on the available performance of students. To this end, this paper presents an in-depth analysis of deep learning and machine learning approaches for the formulation of an automated students’ performance estimation system that works on partially available students’ academic records. Our main contributions are: (a) a large dataset with 15 courses (shared publicly for academic research);(b) statistical analysis and ablations on the estimation problem for this dataset;(c) predictive analysis through deep learning approaches and comparison with other arts and machine learning algorithms. Unlike previous approaches that rely on feature engineering or logical function deduction, our approach is fully data-driven and thus highly generic with better performance across different prediction tasks. The main takeaways from this study are: (a) for better prediction rates, it is desirable to have multiple low weightage tests than few very high weightage exams;(b) the latent space models are better estimators than sequential models;(c) deep learning models have the potential to very accurately estimate the student performance and their accuracy only improves as the training data are increased. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2021.

关键词： COVID-19 Deep neural network Educational institutions Variational auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Physical-layer security in MU-MISO downlink networks against potential eavesdroppers

引用

Digital Communications and Networks 2025年第2期11卷 424-431页

作者： Woong Son Minkyu Oh Heejung Yu Bang Chul Jung C4I R&D Lab. LIG Nex1 Co.Ltd.Yongin16911South Korea Department of Electronics Engineering Chungnam National UniversityDaejeon34134South Korea Department of Electronics and Information Engineering Korea UniversitySejong30019South Korea Department of Electrical and Computer Engineering Ajou UniversitySuwon16499South Korea

Recently,wireless security has been highlighted as one of the most important techniques for 6G mobile communication *** researchers have tried to improve the Physical-Layer Security(PLS)performance such as Secrecy Outage Probability(SOP)and Secrecy Energy-Efficiency(SEE).The SOP indicates the outage probability that the data transmission between legitimate devices does not guarantee a certain reliability level,and the SEE is defined as the ratio between the achievable secrecy-rate and the consumed transmit *** this paper,we consider a Multi-User Multi-Input Single-Output(MU-MISO)downlink cellular network where a legitimate Base Station(BS)equipped with multiple transmit antennas sends secure information to multiple legitimate Mobile Stations(MSs),and multiple potential eavesdroppers(EVEs)equipped with a single receive antenna try to eavesdrop on this *** potential EVE tries to intercept the secure information,i.e.,the private message,from the legitimate BS to legitimate MSs with a certain eavesdropping *** securely receive the private information,each legitimate MS feeds back its effective channel gain to the legitimate BS only when the effective channel gain is higher than a certain threshold,i.e.,the legitimate MSs adopt an Opportunistic Feedback(OF)*** such eavesdropping channels,both SOP and SEE are analyzed as performance measures of PLS and their closed-form expressions are derived *** on the analytical results,it is shown that the SOP of the OF strategy approaches that of a Full Feedback(FF)strategy as the number of legitimate MSs or the number of antennas at the BS ***,the trade-off between SOP and SEE as a function of the channel feedback threshold in the OF strategy is *** analytical results and related observations are verified by numerical simulations.

关键词： Physical-layer security Opportunistic feedback Potential eavesdroppers Secrecy outage probability Secrecy energy-efficiency

来源：评论

学校读者我要写书评

暂无评论

Determination of 24-Hour EV Hosting Capacity of Qatar's Utility Grid Considering Existing Load Patterns and Different Charging Speeds 60

Determination of 24-Hour EV Hosting Capacity of Qatar's Util...

引用

60th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2024

作者： Rahman, Syed Khan, Irfan Ayaz, Muhammad Ashar Iqbal, Atif Su, Chun-Lien Texas A&m University Electrical & Computer Engineering College Station United States Lab Galveston United States Qatar University Department of Electrical Engineering Doha Qatar National Kaohsiung University of Science & Technology Department of Electrical Engineering Taiwan

ISBN: (纸本)9798350345308

The widespread adoption of electric vehicles (EVs) has induced profound transformations in the resulting power demand and voltage profile of the low-voltage utility grids. The impact of this paradigm shift is contingent upon subtle factors, including the power rating of EV chargers, point of installation, prevailing power demand profiles, and driving patterns (dictating kWh energy of EV load). The introduction of EV loads without considering these factors and the subsequent comprehensive analysis will result in grid congestion, heightened peak demand, and augmented system losses. To address this, this paper presents a comprehensive case study of determining the EV hosting capacity of Qatar's utility grid, considering real-world demand profile data, existing load types, and their corresponding variation pattern. Secondly, considering the energy and instantaneous power requirement of EV load, the EV hosting is estimated using a 24-hour profile considering all EV charger types (DC fast chargers, level-2 chargers, and domestic chargers). A 2-step optimization algorithm is proposed to maximize the hosting capacity by optimally distributing the charging load among the residential nodes, without any events of grid congestion. Detailed simulation results show that EV charging load up to 11.4% of the distribution system rating can be accommodated without grid congestions. © 2024 IEEE.

关键词： Electric load flow

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：