检索结果-内蒙古大学图书馆

5th International Conference on computing and Network Communications, CoCoNet 2023

作者： Surisetty, Hima Varshini Gottimukkala, Sarayu Varma Vekkot, Susmitha Gupta, Deepa Alotaibi, Yousef A. M. Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Bengaluru India Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh11451 Saudi Arabia

ISBN: (纸本)9789819747108

Aphasia is one of the brain disorders that affects the part of the brain that is responsible for communication. This work deals with the detection of aphasia from speech features. The features extracted from the speech samples are MFCC, mel spectrogram, zero crossing rate, chroma, energy, spectral centroid, spectral roll-off, fundamental frequency and utterance duration. These different speech features were then ranked based on the SHapley Additive exPlanations (SHAPs), and the most important features were retained in an optimized feature set that was given to various machine learning models like support vector machine and decision trees and deep learning models like LSTM, LSTM with GRU, Bi-LSTM and Bi-LSTM with GRU. These models were then evaluated based on their train and test set accuracy, F1 score, recall, precision, plots of training loss and validation loss and confusion matrix. Based on the analysis of the performance metrics, Bi-LSTM with GRU was found to be the best model among all the models used. The model’s performance was evaluated using metrics like accuracy, F1 score, recall and precision when trained and tested with the optimal feature set which were 87.5%, 79.7%, 90% and 75%, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Multiagent Deep-Reinforcement-Learning-Based Cooperative Perception and Computation in VEC

引用

IEEE Internet of Things Journal 2025年第12期12卷 21350-21363页

作者： Zhao, Liang Li, Longjia Tan, Zhiyuan Hawbani, Ammar He, Qiang Liu, Zhi Shenyang Aerospace University School of Computer Science Shenyang110136 China Edinburgh Napier University School of Computing EdinburghEH10 5DT United Kingdom Northeastern University School of Medicine and Biological Information Engineering Shenyang110169 China The University of Electro-Communications Department of Computer and Network Engineering Tokyo1828585 Japan

Connected and autonomous vehicles (CAVs) are an important paradigm of intelligent transportation systems. Cooperative perception (CP) and vehicular edge computing (VEC) enhance CAVs’ perception capacity of the region of interest (RoI) while alleviating the pressure of intensive computation on onboard resources. However, existing CP and computation schemes are based on inefficient broadcast communications and still face challenges, such as highly dynamic communication link channel conditions caused by vehicle mobility, and limited computing resources in VEC environments. Considering the delay sensitivity of CAVs’ perception tasks and the need for enhanced perception, we propose a unicast-based cooperative perception and computation scheme to achieve more efficient resource utilization and perception task execution in VEC scenarios. Our goal is to maximize CP gain and minimize task execution delay by optimizing the decision of each ego CAVs. To solve the sequential decision-making problem of multiobjective optimization, we propose a solution based on improved multiagent proximal policy optimization deep reinforcement learning, where CAVs agents make adaptive decisions distributed based on partial observations. Simulation results show that compared with the baseline algorithm, our proposed scheme effectively reduces the execution delay of ego CAVs perception tasks and ensures a high perception gain. © 2014 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Random Forests for Ovarian Cancer Detection and Precision Prediction 7

Leveraging Random Forests for Ovarian Cancer Detection and P...

引用

7th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2023

作者： Inture, Anvita Reddy Sai Nadh, Boddu Sasi Sha, Akhbar Abhishek, S. Anjali, T. Mullapudi, Taraka Vignesh Amrita School of Computing Department of Computer Science and Engineering Amritapuri India Grainger Engineering University of Illinois Urbana Department of Computer Science Champaign United States

ISBN: (纸本)9798350340600

This study has employed machine learning techniques for the critical task of ovarian cancer detection, utilizing a comprehensive dataset: Mendeley Data, V11. Our approach involved the application of a Random Forest classifier to a dataset comprising 50 relevant features. To mitigate the risk of overfitting and enhance model robustness, we randomly divided these features into subsets of 10, iteratively training and testing the classifier. The final prediction was based on the majority vote from five classifiers. Our results demonstrated remarkable success in ovarian cancer detection. The Random Forest classifier exhibited an outstanding accuracy of 0.98 on the test dataset, indicating its proficiency in distinguishing between ovarian cancer cases and non-cancer cases. Precision-Recall analysis further underscored the model's effectiveness, with an impressive average precision (AP) of 0.98. This high AP value underscores the model's capability to provide highprecision predictions, which is particularly crucial in medical applications, where minimizing false alarms is of paramount importance. These findings underscore the potential of machine learning, specifically Random Forest, as a valuable tool in ovarian cancer detection. The combination of feature subset selection and ensemble learning techniques led to a robust and reliable predictive model. While these results are promising, ongoing validation and collaboration with domain experts are essential steps toward the translation of this research into clinical practice, where early and accurate cancer detection can have a profound impact on patient outcomes. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Improved MPPT algorithm: Artificial neural network trained by an enhanced Gauss-Newton method

AIMS Electronics and Electrical Engineering

引用

AIMS Electronics and electrical engineering 2023年第4期7卷 380-405页

作者： Dkhichi, Fayrouz Laboratory of Networks Computer Science Telecommunications & Multimedia Electrical Engineering Department Superior School of Technology Hassan II University of Casablanca Morocco

A novel approach defined by the artificial neural network (ANN) model trained by the improved Gauss-Newton in conjunction with a simulated annealing technique is used to control a step-up converter. To elucidate the superiority of this innovative method and to show its high precision and speed in achieving the right value of the Maximum Power Point (MPP), a set of three comparative Maximum Power Point Tracker (MPPT) methods (Perturbation and observation, ANN and ANN associated with perturbation and observation) are exanimated judiciously. The behavior of these methods is observed and tested for a fixed temperature and irradiance. As a result, the proposed approach quickly tracks the right MPP = 18.59 W in just 0.04382 s. On the other hand, the outstanding ability of the suggested method is demonstrated by varying the irradiance values (200 W/m , 300 W/m , 700 W/m , 1000 W/m , 800 W/m and 400 W/m ) and by varying the temperature values (15°C, 35°C, 45°C and 5°C). Therefore, the ANN trained by Gauss-Newton in conjunction with simulated annealing shows a high robustness and achieves the correct value of MPP for each value of irradiance with an efficiency 99.54% and for each value of temperature with an efficiency 99.98%;the three other methods sometimes struggle to achieve the right MPP for certain irradiance values and often remains stuck in its surroundings. © 2023 The Author(s).

关键词： Maximum power point trackers

来源：评论

学校读者我要写书评

暂无评论

KiAtt Fusion: Remote Sensing-Based Water Bodies Segmentation for Environmental Monitoring 4

KiAtt Fusion: Remote Sensing-Based Water Bodies Segmentation...

引用

4th International Conference on Digital Futures and Transformative Technologies, ICoDT2 2024

作者： Sikander, Saad Rehman, Hamood Ur Naqvi, Syed Fakhr Abbas Aslam, Waqar Perwaiz, Nazia Sir Syed CASE Institute of Technology Department of Electrical Engineering Islamabad Pakistan Sir Syed CASE Institute of Technology Department of Electrical Engineering and Computer Science Islamabad Pakistan National University of Sciences and Technology NUST School of Electrical Engineering and Computer Science Islamabad Pakistan

ISBN: (纸本)9798350391862

Monitoring the environment and managing water bodies are crucial for preserving ecosystems and ensuring sustainable resource utilization. This study aims to propose a robust approach for segmenting water bodies by combining various complementary attributes extracted from deep learning techniques. By leveraging deep contextual features learned from attention regions and enhanced edge detection, our method significantly improves the accuracy of detecting water bodies in low-resolution satellite imagery. Utilizing S1 and S2 Sentinel imagery data and exploring multi-band features, we enhance key attributes through advanced UNet architectures - specifically, Ki-UNet and Attention UNet - and integrate complementary features for downstream tasks. Additionally, we assembled a local dataset from the Khyber Pakhtunkhwa (KPK) region of Pakistan, facilitating precise water body segmentation from satellite or aerial views. Our ensemble model achieved remarkable accuracy and Intersection over Union (IoU) scores, reaching up to 99.01% and 96.2%, respectively, surpassing state-of-the-art models. This research provides automated, accurate segmentation techniques essential for environmental management and resource assessment, offering a promising solution for delineating water bodies. github link : (https://***/SaadBaloch96/Dataset/blob/main/***) © 2024 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Detecting Counterfeit Indian Currency A Comparative Analysis of Machine Learning Algorithms and Image Processing 15

Detecting Counterfeit Indian Currency A Comparative Analysis...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Vyshnavi, M.R.V. Varshitha, N.L. Harshith Kumar, Konda V. S. Singh, Tripty Sharma, Mansi Chatterjee, Suman Amrita School of Computing Department of Computer Science Engineering Bengaluru India Dehradun India Kongju National University Department of Mechanical Engineering Cheonan Korea Republic of

ISBN: (纸本)9798350370249

The degree of secured currency is one of the key areas that makes its contribution in solving the problem of economic insecurity, highlights the most important. Even as it can be quite strained to actually identify which precise time frame this fake process was prepared in, complex fakes render the use of validation techniques quite challenging. This paper has aimed at displaying and evaluating the overall outcome of the different strategies of image, and the acquired classifiers in the identification of the fake FI currency. The following are the subsequent of the other operation that was applied in order to achieve the objectives of the intended work;Image capture This is whereby the images to be used are taken by the appropriate camera or scanner. Others used include the Naïve Bayes, Support Vector Classifier and Gradient Descent and Artificial Neural Network in this paper. As in the conclusion, with the help of the mathematical formulation, it can be confirmed that in fact, within an experiment, Neural Networks do have a higher level of optimization, much more than an average image processing if it is provoked to identify fake notes. In other words if used and implemented with the best of the machine learning approach and best of the image processing method then solitaire for detection of the counterfeit currency can be made more dependable than all the combined methods stated above. The objective of this study is to build and compare the performance of different machine learning algorithms and image processing methodologies for the identification of fake Indian currency notes. © 2024 IEEE.

关键词： Counterfeit Detection Gradient Descent Image Processing Machine Learning Mathematical Formulation Naïve Bayes Neural Networks Support Vector Classifier

来源：评论

学校读者我要写书评

暂无评论

DiminishAR: Diminishing Visual Distractions via Holographic AR Displays 25

DiminishAR: Diminishing Visual Distractions via Holographic ...

引用

2025 CHI Conference on Human Factors in computing Systems, CHI 2025

作者： Lee, JangHyeon Kim, Lawrence H. Department of Computer Science & Engineering University of Minnesota MinneapolisMN United States School of Computing Science Simon Fraser University Burnaby Canada

ISBN: (纸本)9798400713941

Smartphones are integral to modern life, yet research highlights the cognitive drawbacks associated with their mere presence. While physically removing them can mitigate these effects, it is often inconvenient and may heighten anxiety due to prolonged separation. To address this, we use holographic augmented reality (AR) displays to visually diminish distractions with two interventions: 1) Visual Camouflage, which disguises the smartphone with a hologram that matches its size and blends with the background, making it less noticeable, and 2) Visual Substitution, which occludes the smartphone with a contextually relevant hologram, like books on a desk. In a study with 60 participants, we compared cognitive performance with the smartphone nearby, remote, and visually diminished by our AR interventions. Our findings show that the interventions significantly reduce cognitive impairment, with effects comparable to physically removing the smartphone. The adaptability of our approach opens new avenues to manage visual distractions in daily life. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Systematic Review of Emerging Deep Learning approaches for Crop Diseases detection 7

Systematic Review of Emerging Deep Learning approaches for C...

引用

7th International Conference on Circuit Power and computing Technologies, ICCPCT 2024

作者： Vasuki Rohinidevi, V. Deeban Chakravarthy, V. Deepak, S. Prem Kumar SRM Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India B V Raju Institute of Technology Department of Computer Science and Engineering Narsapur India

ISBN: (纸本)9798350372816

Deep learning, a branch of artificial intelligence, has drawn interest from the academic and corporate realms, especially in areas like speech and image analysis, video processing, and natural language processing. Its use in agricultural plant protection has expanded to include the diagnosis and evaluation of pests and plant diseases. In this situation, there are several benefits to using deep learning. It removes the biases related to manually chosen pathogen properties, improves objectivity when determining disease characteristics, and hastens the advancement of contemporary technology. In order to diagnose agricultural leaf illnesses, this study explores the most recent developments in deep learning methods, including CNN, DENSNET, InceptionV3, VGG16, Resnet50, and MobileNet, in addition to a variety of sensors. This project aims to aid scientists in the field by tackling challenges in merging deep learning and cutting-edge imaging tools to enhance illness identification. It addresses current trends and barriers, shedding light on unresolved issues and paving the way for further research. By clarifying persistent problems and posing new questions, it fosters progress and innovation in the field of medical imaging and diagnosis. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicular Twin Networks

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicu...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Al-Shareeda, Sarah Ozguner, Fusun Redmill, Keith Duong, Trung Q. Canberk, Berk The Ohio State University Electrical and Computer Engineering Department United States Bts Group Turkey Istanbul Technical University Department of Ai and Data Engineering Turkey School of Electronics Electrical Engineering and Computer Science Queen's University Belfast United Kingdom Memorial University of Newfoundland Faculty of Engineering and Applied Science St. John'sNL Canada School of Computing Engineering and The Built Environment Edinburgh Napier University United Kingdom

ISBN: (纸本)9798350368369

Task offloading management in 6G vehicular net-works is crucial for maintaining network efficiency, particularly as vehicles generate substantial data. Integrating secure communication through authentication introduces additional computational and communication overhead, significantly impacting offloading efficiency and latency. This paper presents a unified framework incorporating lightweight Identity-Based Cryptographic (IBC) authentication into task offloading within cloud-based 6G Vehicular Twin Networks (VTNs). Utilizing Proximal Policy Optimization (PPO) in Deep Reinforcement Learning (DRL), our approach optimizes authenticated offloading decisions to minimize latency and enhance resource allocation. Performance evaluation under varying network sizes, task sizes, and data rates reveals that IBC authentication can reduce offloading efficiency by up to 50% due to the added overhead. Besides, increasing network size and task size can further reduce offloading efficiency by up to 91.7%. As a countermeasure, increasing the transmission data rate can improve the offloading performance by as much as 63%, even in the presence of authentication overhead. The code for the simulations and experiments detailed in this paper is available on GitHub for further reference and reproducibility [1]. © 2025 IEEE.

关键词： Authentication Deep Reinforcement Learning Identity-Based Cryptography Proximal Policy Optimization Task Offloading Vehicular Twin Networks

来源：评论

学校读者我要写书评

暂无评论

Finite-Time Synchronization of Complex Networks With Intermittent Couplings and Neutral-Type Delays

引用

IEEE/CAA Journal of Automatica Sinica 2023年第10期10卷 2026-2028页

作者： Engang Tian Yi Zou Hongtian Chen School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai 200093China Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China

Dear Editor, This letter focuses on the finite-time synchronization(FTS) of neutral-type complex networks with intermittent couplings. Different from most of the existing references concerning neutral-type systems,a delay-independent dynamical event-triggering controller is considered, operating the same way as the intermittent coupling and excluding the Zeno behavior naturally.

关键词： neutral letter concerning

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：