检索结果-内蒙古大学图书馆

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Xiong Yan Kedong Yan Chanying Huang Dan Yin Shan Xiao School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Comp. Science & Engineering Nanjing Univ. of Science & Technology Nanjing China School of Elec. & Inf. Engineering Beijing Univ. of Civil Engineering & Architecture Beijing China Fiberhome Comm. Tech. Co. Wuhan China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

Federated Learning enables multiple clients to collaboratively train a model without sharing their individual data, thereby protecting local data privacy. However, attackers, such as untrusted servers, can still compromise the privacy of clients’ local training data through various inference attacks. One feasible approach to protect client privacy during training is the incorporation of differential privacy. Nevertheless, achieving an ideal level of privacy protection with differential privacy often degrades the model’s performance, significantly reducing its accuracy. To enhance model accuracy while minimizing the additional client heterogeneity introduced by differential privacy, this paper proposes a method that integrates personalized layers and data transformations, FusTP-FL. The core of our FusTP-FL is the incorporation of personalized layers and personalized data transformations within the client’s local training model, which further reduces client heterogeneity and improves model accuracy. We evaluated the model’s accuracy on six common datasets; experimental results demonstrate that the proposed FusTP-FL effectively enhances model accuracy across two different differential privacy modes (CDP and LDP), increasing it by up to 45%. Furthermore, we show that compared to PRIVATEFL, our method achieves lower client heterogeneity.

关键词： Training Differential privacy Privacy Accuracy Federated learning Computational modeling Training data Data models Servers Security

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Prediction Using Machine Learning Algorithms 8

Cardiovascular Disease Prediction Using Machine Learning Alg...

引用

8th IEEE International Conference on engineering Technologies and Applied sciences, ICETAS 2023

作者： Bagadi, Kalapraveen Annepu, Visalakshi Jameel Al-Tamimi, Adnan Naji Challa, Naga Raju Aljibori, H.S.S. Mohammed, M.N. Abdullah, Oday I. Abbas Helmi, Rabab Alayham Alfiras, M. School of Electronics Enineering VIT-AP University Amaravati India School of Comp. Science & Eng. VIT-AP University Amaravati India College of Technical Engineering Al-Farahidi University Baghdad Iraq Bapatla Engineering College Dept. of Elec. and Comm. Eng. Baptla India College of Engineering University of Warith Al-Anbiyaa Karbala Iraq College of Engineering Gulf University Mechanical Engineering Department Sanad26489 Bahrain University of Baghdad Dept of Energy Engineering Iraq College of Engineering Gulf University Mechanical Engineering Dept Sanad26489 Bahrain Hamburg University of Technology Institute of Laser and Systems Technologies Hamburg Germany School of Graduate Studies Management and Science University Selangor Shah Alam Malaysia College of Engineering Gulf University Electrical and Electronic Engineering Department Sanad26489 Bahrain

ISBN: (纸本)9798350327090

The fact that cardiovascular disease (CVD) is a major cause of death worldwide highlights the significance of accurate prediction for successful preventative and treatment measures. Machine learning algorithms, which use the analysis of vast patient data to reveal hidden patterns and risk variables, have recently come to light as potential techniques for CVD prediction. This study intends to analyse how machine learning (ML) techniques are used in CVD prediction and evaluate how well they perform in comparison to conventional approaches. The study makes use of a sizable patient cohort's medical history, demographic data, and clinical factors in a complete dataset. Predictive models are built using a variety of machine learning algorithms, including support vector machine (SVM), gradient boosting, K-nearest neighbours, naive Bayes classifier, and logistic regression. To find the most important factors influencing CVD risk, feature selec.ion techniques are used. Metrics like accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve are used to assess how well the machine learning models work. The outcomes are contrasted with well-known risk prediction models and clinical guidelines in order to assess the added value of machine learning methods. This work intends to improve CVD prediction capabilities and offer useful insights for better risk assessment and management strategies by utilizing the power of machine learning. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Embedded Acoustic Noise Cancellation (ANC) Performances Analysis for Voice Communications using Linear Adaptive Approaches 23

Embedded Acoustic Noise Cancellation (ANC) Performances Anal...

引用

6th International Conference on Networking, Intelligent Systems and Security, NISS 2023

作者： Wahbi, Azeddine Ouchatti, Abderrahmane Elghayyaty, Mohamed El Habti El Idrissi, Anas Roukhe, Ahmed Bensassi, Bahloul Hlou, Laamari Lab. of Elec. and Industrial Engineering Information Processing Computer Sciences and Logistic Faculty of Sciences Ain Chock Casablanca Hassan Ii University Maarif Casablanca Morocco Laboratory of Electronic Systems Information Processing and Energetics Faculty of Sciences Ibn Tofail University Kenitra Morocco Laboratory of Atomic Mechanical Photonics and Energy Faculty of Science University Moulay Ismail Meknes Morocco

ISBN: (纸本)9798400700194

ANC systems have emerged as the most widely adopted technologies in voice communications. This paper purpose a comparison between the adaptive approaches in time and frequency domain, which is used to model, design and implement these systems. All designs are developed by creating new embedded blocks using Simulink environment. Furthermore, the performance of the proposed embedded designs based adaptive algorithm is analyzed and evaluated on the basis of Signal to Noise Ratio (SNR) and computational complexity improvement, where these designs are applied on ANC to compensate linear distortion in the noise path. Moreover, the produced results showed that using embedded blocks based adaptive algorithm in frequency domain gives the best result than the rest of the other embedded designs. © 2023 ACM.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Automatic detection and prevention of breast cancer by ML algorithms with dimensionality reduction technique PCA

Automatic detection and prevention of breast cancer by ML al...

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Mohd Firoz Warsi Shiv Narain Gupta Usha Chauhan Rahul Dev Rakhi Bhardwaj Abhishek Kaushik Department of Computer Science (AIDS) Greater Noida Institute of Technology Greater Noida Uttar Pradesh India Department of Elec. and Comm. Engg. Greater Noida Institute of Technology Greater Noida Uttar Pradesh India Department of Elec. and Comm. Engg. Galgotias University Greater Noida Uttar Pradesh India Department of Elec. and Comm. Engg. GL Bajaj Institute of Tech. & Mgmt. Greater Noida Uttar Pradesh India Department of Computer Sci. and Engg. College of Smart Computing COER University Roorkee Uttar Pradesh India Department of Elec. and Comm. Engg. Vishveshwarya Group of Institutions G. B. Nagar Uttar Pradesh India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

Early detection and prevention of breast cancer are vital for improving patient outcomes and reducing mortality rates. Machine learning algorithms, coupled with principal component analysis (PCA), offer a promising approach for enhancing the accuracy and efficiency of breast cancer diagnosis. This paper proposes a novel approach to early breast cancer detection, combining machine learning algorithms, including support vector machines, neural networks, and random forests, with PCA. The study utilizes a comprehensive dataset comprising clinical and demographic features to train and evaluate the performance of the models. Results demonstrate the efficacy of the proposed approach in accurately identifying breast cancer at its early stages, thus enabling timely intervention and improved patient care. Furthermore, the integration of PCA aids in reducing dimensionality and enhancing the interpretability of the models thereby is facilitating more effective decision-making in clinical settings. Overall, this research underscores the potential of machine learning algorithms with PCA in revolutionizing breast cancer detection and prevention strategies, ultimately contributing to better healthcare outcomes and patient wellbeing. In this study we have applied five ML technique: Logistic Regression, Decision tree, Random forest, Naïve byes and support vector machine on the Breast Cancer Wisconsin Diagnostic dataset. The evaluation of classification outcomes was conducted both with and without the implementation of PCA. Notably, upon applying PCA, the random forest classifier emerged as the top performer, surpassing all other classifiers. Impressively, it attained an accuracy rate of 99.8%, showcasing its superior performance in the dataset.

关键词： Support vector machines Dimensionality reduction Logistic regression Machine learning algorithms Prevention and mitigation Decision making Medical services Breast cancer Random forests Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Natural Language Instructions for Intuitive Human Interaction with Robotic Assistants in Field Construction Work

arXiv

引用

arXiv 2023年

作者： Park, Somin Wang, Xi Menassa, Carol C. Kamat, Vineet R. Chai, Joyce Y. Dept. of Civil and Env. Engineering University of Michigan United States Dept. of Construction Science Texas A&M University United States Dept. of Elec. Engineering and Computer Science University of Michigan United States

The introduction of robots is widely considered to have significant potential of alleviating the issues of worker shortage and stagnant productivity that afflict the construction industry. However, it is challenging to use fully automated robots in complex and unstructured construction sites. Human-Robot Collaboration (HRC) has shown promise of combining human workers’ flexibility and robot assistants’ physical abilities to jointly address the uncertainties inherent in construction work. When introducing HRC in construction, it is critical to recognize the importance of teamwork and supervision in field construction and establish a natural and intuitive communication system for the human workers and robotic assistants. Natural language-based interaction can enable intuitive and familiar communication with robots for human workers who are non-experts in robot programming. However, limited research has been conducted on this topic in construction. This paper proposes a framework to allow human workers to interact with construction robots based on natural language instructions. The proposed method consists of three stages: Natural Language Understanding (NLU), Information Mapping (IM), and Robot Control (RC). Natural language instructions are input to a language model to predict a tag for each word in the NLU module. The IM module uses the result of the NLU module and building component information to generate the final instructional output essential for a robot to acknowledge and perform the construction task. A case study for drywall installation is conducted to evaluate the proposed approach. The results of the NLU and IM modules show high accuracy over 99%, allowing a robot to perform tasks accurately for a given set of natural language instructions in the RC module. The obtained results highlight the potential of using natural language-based interaction to replicate the communication that occurs between human workers within the context of human-robot teams. Copyri

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Temperature Variations on the Performance of Thermoelec.ric Generators

Analyzing the Impact of Temperature Variations on the Perfor...

引用

elec.rical, Energy, and Artificial Intelligence (EICEEAI), International engineering Conference on

作者： Adel E. M. Yahya Rebha Daw Sarreb Khalid Yahya Hani Attar Mahmoud Aldababsa Mohamed Hafez Dept of Electrical Engineering Sabratah University Regdalen Libya Dept of Computer Engineering Sabratah University Regdalen Libya Dept of Elec. and Electr. Engineering Istanbul gelisim University Istanbul Turkey Dept of Energy Engineering Zarqa University Jordan College of Engineering University of Business and Technology Jeddah Saudi Arabia Dept of Elec. and Electr. Engineering Nisantasi University Istanbul Turkey Faculty of Engineering FEQS INTI-IU-University Nilai Malaysia

ISBN: (数字)9798350373363

ISBN: (纸本)9798350373370

Recent advancements in renewable energy technologies have brought Thermoelec.ric Generators (TEGs) to the forefront, primarily due to their ability to efficiently convert waste thermal energy into elec.rical power across multiple power levels. This study delves into the environmental benefits and operational efficiencies of TEGs, highlighting their zero-emission, silent operation, and low maintenance requirements. A significant portion of this research is dedicated to exploring the influence of temperature differential (ΔT) on the efficacy of TEGs, as temperature is a crucial factor in the energy conversion process. The elec.rical representation of TEGs is modeled as a voltage source in series with an internal resistance, while its thermal aspect comprises parallel-connected p- and n-type thermocouples. The study aims to meticulously analyze the behavior of TEG models under various thermal gradients and to scrutinize their elec.rical characteristics under different load conditions. This is achieved through comprehensive experimental methodologies, with the findings underscoring the impact of temperature variations on both hot and cold sides of TEGs on all elec.rical parameters. It is observed that an increase in the temperature difference results in a corresponding rise in both the maximum power output and the open-circuit voltage. In essence, the efficiency of TEGs is noted to improve with a higher and more stable temperature differential.

关键词： Renewable energy sources Temperature Thermal resistance Thermocouples Generators Thermal analysis Thermal loading

来源：评论

学校读者我要写书评

暂无评论

Sub-Picosecond-Level Laser-Based Underwater Transfer of Radio Frequency with Optical Phase Compensation 20

Sub-Picosecond-Level Laser-Based Underwater Transfer of Radi...

引用

20th IEEE International Conference on Communication Technology, ICCT 2020

作者： Pan, Bisong Li, Haopengyu Hou, Dong Zhao, Jianye Univ. of Electronic Science and Technology of China School of Automation Engineering Chengdu China Peking University College of Elec. Engineering and Computer Science Beijing China

ISBN: (纸本)9781728181417

We demonstrated a sub-picosecond laser-based underwater frequency transfer with an optical phase compensation. With this transfer technique, a highly-stable 500 MHz radio-frequency (RF) signal was disseminated over a 5-m underwater link for 5000 s, and the characteristic of the timing fluctuation and instability for the transfer was analyzed and measured. The experimental results show the total root-mean-square (RMS) timing fluctuation of the transferred RF signal with compensation is about 162 fs with a fractional frequency instability on the order of 2.8 × 10-13 at 1 s and 2.7 × 10-16 at 1000 s. The laser-based underwater frequency transfer proposed in this paper has a potential application of transferring atomic clock in water environment as its instability is less than the currently-used commercial Cs or H-master clocks. © 2020 IEEE.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Geometric-Aware Facial Landmark Emotion Recognition

Geometric-Aware Facial Landmark Emotion Recognition

引用

Software engineering and computer science (CSECS), International Conference on

作者： Qixuan Zhang Zhifeng Wang Yang Liu Zhenyue Qin Kaihao Zhang Tom Gedeon College of Engineering and Computer Science Australian National University Canberra Australia School of Elec Eng Comp and Math Sci Curtin University Perth Australia

Emotion recognition is crucial for enhancing human-computer interaction. While traditional approaches largely depend on RGB images, our proposed Geometric-Aware Facial Landmark Emotion Recognition framework harnesses the geometric and spectral attributes of facial landmarks for emotion recognition. This work unfolds three key contributions: utilizing Graph Convolutional Networks to grasp the natural spatial relationships among facial landmarks, introducing distance-aware graph operations to accentuate the relational geometry, and employing spectral encodings to comprehend the frequency-based attributes of landmark positions. Through rigorous experiments on recognized datasets RAF-DB and KDEF, Our method surpasses baseline methods, demonstrating its effectiveness especially in high-resolution scenarios where detailed facial landmarks are apparent. The datasets curated for Facial Landmark Emotion Recognition will also be shared publicly as part of this work, offering a significant resource for the community. The encouraging results highlight the potential of geometric-aware analysis in propelling emotion recognition systems forward, opening avenues for further research in this evolving domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous Drone Landing on a Moving Naval Base using Vision-Based Robot Control

Autonomous Drone Landing on a Moving Naval Base using Vision...

引用

elec.rical, computer, Communications and Mechatronics engineering (ICECCME), International Conference on

作者： Senthil Pon Vignesh Subamanian Suvetha Meenaa Subramanian Padmapriya Muthiah Jalaluddin Mohd Ansari Shajahan Dept. of Elec. and Comm. Engg. SIMATS School of Engineering Saveetha University Chennai India Dept. of Computer Science City College of New York City University of New York New York USA Dept. of Computer Science King Graduate School Monroe College New York USA Dept. of Electrical Engineering City College of New York City University of New York New York USA

This paper proposes a novel technique of an Autonomous Drone landing on top of a moving Naval Vessel Base using Vision-Based Robot Control. To achieve an effective landing a camera is fixed under the drone which captures the images and detects the movement of the landing base. The landing base on top of the vessel is specially designed with a nested tag which is scanned by the fixed camera on the drone from a high altitude. This nested tag is a fiducial marker that is used by the imaging system of the drone as a point of reference in the Naval Vessel Base for precise landing. The controller is designed in the image coordinate frame captured by the imaging system on the drone with the help of the Jacobian Matrix. Whether the vessel remains stationary or moving, it always trembles, especially, when a vessel experiences bad weather at sea, it will be quite challenging for the drone to land on the trembling Naval Vessel Base. These unexpected movements cause the landing tag to disorient from the horizontal view of the captured frames, which makes it difficult to obtain the expected mid-point of the tag. To overcome this complication the translational and rotational motions of the drone are decoupled from the camera using the Virtual Camera Method where the mid-point of the tag is set as the feature point which helps to obtain the expected position during the horizontal plane disorientation of the tag image captured by the camera from the drone. Additionally, Kalman Filter is employed in the imaging system to reduce the observation noise so that precise estimation of the feature point can be achieved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Charging Solutions for 400V EV Batteries: Implementing a Quasi Single-Stage Current-Fed Resonant Converter

Robust Charging Solutions for 400V EV Batteries: Implementin...

引用

IEEE Texas Power and Energy Conference (TPEC)

作者： Muhammad Furqan Waqar Uddin Kamran Zeb Muhammad Ashar Ayaz Irfan Khan Muhammad Khalid School of Electrical Engineering and Computer Science (SEECS) National University of Science and Technology (NUST) Islamabad Pakistan Interdisciplinary Research Center for Sustainable Energy Systems (IRC-SES) King Fahd University of Petroleum and Minerals (KFUPM) Dhahran Saudi Arabia IRC-SES KFUPM Dhahran Saudi Arabia Dept. of Electrical and Computer Engneering Texas A and M University College Station TX USA Dept. of Elec. and Comp. Engineering Texas A and M University College Station TX USA Electrical Engineering Department KFUPM and IRC-SES KFUPM Dhahran Saudi Arabia

ISBN: (数字)9798331541125

ISBN: (纸本)9798331541132

This work presents a high-performance AC-DC quasi single-stage current-fed resonant converter based elec.ric vehicles (EVs) charger. A non-linear control technique is applied which has two main objectives i.e; Power factor correction (PFC) and regulation of DC output voltage. For this purpose, super twisting sliding mode control (ST-SMC) is suggested in this study for 400V batteries of EVs. To reduce switching losses and improve efficiency, the secondary side switch shows turn OFF with zero voltage switching (ZVS) while the primary ones exhibit ZVS at turn ON instant. Hardware-in-loop (HIL) experimental validation based on the Delfino F28369D dual-core microcontroller is used to verify the performance of the controller and converter simulated on PSIM and MATLAB/Simulink.

关键词： Microcontrollers Switching loss Switches Resonant converters Zero voltage switching Regulation Batteries Safety Voltage control Sliding mode control

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：