检索结果-内蒙古大学图书馆

8th International Symposium on Intelligent Informatics, ISI 2023

作者： Shenbaga Moorthy, Rajalakshmi Arikumar, K.S. Prathiba, Sahaya Beni Pabitha, P. Sri Ramachandra Faculty of Engineering and Technology Sri Ramachandra Institute of Higher Education and Research Chennai600 116 India Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur Chennai603 203 India Centre for Cyber Physical Systems School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India Department of Computer Technology Anna University Madras Institute of Technology Campus Chennai600044 India

ISBN: (纸本)9789819721467

Accurate solutions are needed for a variety of computer vision applications, including medical imaging, object detection, and recognition. Such complicated challenges are beyond the capabilities of artificial intelligence and machine learning, which mainly rely on data and algorithms to learn. The path to Deep Learning (DL) is thus paved. Even though deep learning is incredibly effective at solving complex problems, it is invariant, meaning that it ignores the spatial relationship between the features and instead searches for features only. This can cause the model’s performance to suffer. Additionally, because the model is invariant, gathering a large volume of training data is a difficult undertaking. To address this, the Capsule Network (CapsNet), whose performance outperforms Deep Learning techniques, was introduced. Despite its success, applications of CapsNet and working remain a mystery. Thus, the performance of CapsNet across many applications and obstacles is examined in this study together with the predecessors of CapsNet. Additionally, this paper explores the use of Capsule Networks with an attention mechanism (CapsNet-ATM) for predicting potato leaf diseases. The performance of CapsNet-ATM in this crucial agricultural application is thoroughly assessed and contrasted with the well-known models VGG-16 and VGG-19, providing insight into the system’s efficacy and promise as a reliable tool for the detection and prediction of potato leaf disease. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer

PSST: A Benchmark for Evaluation-driven Text Public-Speaking...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Sun, Huashan Wu, Yixiao Ye, Yuhao Yang, Yizhe Li, Yinghao Li, Jiawei Gao, Yang School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China

ISBN: (纸本)9798891761681

Language style is necessary for AI systems to understand and generate diverse human language ***, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application *** overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking *** in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of *** such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized *** experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

HeartPrint: Passive Heart Sounds Authentication Exploiting In-Ear Microphones 42

HeartPrint: Passive Heart Sounds Authentication Exploiting I...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Cao, Yetong Cai, Chao Li, Fan Chen, Zhe Luo, Jun Beijing Institute of Technology School of Computer Science and Technology China Huazhong University of Science and Technology College of Life Science and Technology China China-Singapore International Joint Research Institute China Nanyang Technological University School of Computer Science and Engineering Singapore

ISBN: (纸本)9798350334142

Biometrics has been increasingly integrated into wearable devices to enhance data privacy and security in recent years. Meanwhile, the popularity of wearables in turn creates a unique opportunity for capturing novel biometrics leveraging various embedded sensing modalities. In this paper, we study a new intracorporal biometrics combining the uniqueness of i) heart motion, ii) bone conduction, and iii) body asymmetry. Specifically, we design HeartPrint as a passive yet secure user authentication system: it exploits the bone-conducted heart sounds captured by (widely available) dual in-ear microphones (IEMs) to authenticate users, while neatly leveraging IEMs renders itself transparent to users without impairing the normal functions of earphones. To suppress the interference from other body sounds and audio produced by the earphones, we develop a novel interference elimination method using modified non-negative matrix factorization to separate clean heart sounds from background interference. We further explore the uniqueness of IEM-recorded heart sounds in three aspects to extract a novel biometric representation, based on which HeartPrint leverages a convolutional neural model equipped with a continual learning method to achieve accurate authentication under drifting body conditions. Extensive experiments with 18 pairs of commercial earphones on 45 participants confirm that HeartPrint can achieve 1.6% FAR and 1.8% FRR, while effectively coping with major attacks, complicated interference, and hardware diversity. © 2023 IEEE.

关键词： Microphones

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of regression models to predict the performance of the dual fuel engine operating on diesel and hydrogen gas

引用

International Journal of Hydrogen Energy 2025年 141卷 585-597页

作者： S, Priya Feenita, C. Goel, Uday T, Manoranjitham Duraisamy, Boopathi Subramanian, Balaji Ganeshan, Kavitha Josephin JS, Femilda Albeshr, Mohammed F. Pugazhendhi, Arivalagan Varuvel, Edwin Geo Department of Computing Technologies College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603 203 India Department of Automobile Engineering College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603 203 India Department of Mechanical Engineering College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603 203 India Department of Science and Humanities Agni College of Technology Thazhambur Chennai600130 India Department of Computer Engineering Faculty of Engineering and Natural Sciences Istinye University Istanbul Turkey Department of Zoology College of Sciences King Saud University P.O. Box. 2455 Riyadh11451 Saudi Arabia Research and Development Office Asia University Taichung City Taiwan Department of Mechanical Engineering Faculty of Engineering and Natural Sciences Istinye University Istanbul Turkey Department of Autoronics Institute of Automobile Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai602105 India

Internal combustion engines (ICEs) have long been essential in both the transportation and industrial sectors, providing primary power for vehicles, ships, and machines globally. Optimising the efficiency of ICEs is vital for decreasing their environmental impart, as increased fuel efficiency and lower emissions play a significant role in mitigating the effects of climate change as well as improving air quality. This study employed 15 regression algorithms and machine learning approaches to analyse and anticipate the performance parameters of ICEs that run on hydrogen-diesel in dual fuel mode. The input parameters include engine torque, speed, hydrogen flow rate, brake power and diesel energy share to hydrogen supply and the output parameters are brake specific fuel consumption, brake thermal efficiency, volumetric efficiency and actual air intake. The model's performance is evaluated using five different performance metrics. Among the studied algorithms, the RANSAC Regressor demonstrated exceptional predictive capability, reaching an R-squared value of 0.999, a mean squared error (MSE) of 0.0064, a root mean square error (RMSE) of 0.08, and a mean absolute error (MAE) of 0.057. These outcomes show the algorithm's accuracy and precision in capturing the complicated data of engine system. The equivalency ratio, volumetric efficiency, brake thermal efficiency, brake specific fuel consumption, and actual air intake are among the critical performance outputs that are optimised by utilizing key input parameters like engine load, rotational speed, hydrogen flow rate, brake power, and the diesel fuel energy share. This study highlights the significant potential of machine learning in optimising ICE performance, offering a reliable alternative to traditional experimental analysis by reducing both risk and economic costs. The research findings also support the paradigm shift towards intelligent and sustainable energy systems by compellingly advocating for the inclusion of da

关键词： Air intakes

来源：评论

学校读者我要写书评

暂无评论

Hybrid AI-Driven Techniques for Enhancing ZeroDay Exploit Detection in Intrusion Detection System (IDS) 3

Hybrid AI-Driven Techniques for Enhancing ZeroDay Exploit De...

引用

3rd International Conference on Artificial Intelligence, Internet of Things and Cloud Computing technology, AIoTC 2024

作者： Tariq, Ahmed Hasham Ibn E Tariq, Moazan Basoud Ibn E Lu, Songfeng School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518063 China

ISBN: (纸本)9798331530280

Zero-day exploits present significant risks to cybersecurity by exploiting unknown vulnerabilities, making their identification and mitigation a key problem. Conventional Intrusion Detection Systems (IDS) frequently depend on signature-based or anomaly-based methodologies, which are ineffective in identifying new and sophisticated incidents of assault. This paper provides a new hybrid AI-driven strategy to boost zeroday exploit detection by the combination of deep learning and ensemble learning approaches. We have taken the UNSW-NB15 dataset, a complete and diversified reference for network intrusion models, to train and analyze our model. The suggested system leverages a hybrid architecture integrating Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to capture both spatial and sequential features of network traffic efficiently. To further increase detection accuracy and resilience, we add ensemble approaches by combining random forest, gradient boosting, and Support Vector Machine (SVM) classifiers through a weighted voting mechanism. Our ensemble model achieves a detection accuracy of 97.8%, outperforming standard anomaly-based (IDS), vision transformer (ViT) and bidirectional encoder representations from transformers (BERT) by a wide margin. The model also demonstrates a low false-positive rate of 0.022 and high detection rates across multiple types of attacks, including previously undiscovered zero-day flaws. Performance studies employing criteria like accuracy, recall, F1score, AUC-ROC, false-positive rate, and detection rate indicate the importance and reliability of our methodology. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization for NOMA-Based Mobile Edge Computing Offloading by Maximizing System Utility

引用

China Communications 2023年第12期20卷 156-165页

作者： Hong Qin Haitao Du Huahua Wang Li Su Yunfeng Peng Chongqing University of Post and Telecom Chongqing 400065China China Mobile Research Institute Beijing 100000China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China

Mobile Edge Computing(MEC)is a technology for the fifth-generation(5G)wireless communications to enable User Equipment(UE)to offload tasks to servers deployed at the edge of ***,taking both delay and energy consumption into consideration in the 5G MEC system is usually complex and ***-orthogonal multiple access(NOMA)enable more UEs to offload their computing tasks to MEC servers using the same spectrum resources to enhance the spectrum efficiency for 5G,which makes the problem even more complex in the NOMA-MEC *** this work,a system utility maximization model is present to NOMA-MEC system,and two optimization algorithms based on Newton method and greedy algorithm respectively are proposed to jointly optimize the computing resource allocation,SIC order,transmission time slot allocation,which can easily achieve a better trade-off between the delay and energy *** simulation results prove that the proposed method is effective for NOMA-MEC systems.

关键词： computation offloading mobile edge computing non-orthogonal multiple access resource allocation

来源：评论

学校读者我要写书评

暂无评论

On convergence of covariance matrix of empirical Bayes hyper-parameter estimator

引用

Control Theory and technology 2024年第2期22卷 149-162页

作者： Yue Ju Biqiang Mu Tianshi Chen School of Data Science and Shenzhen Research Institute of Big Data The Chinese University of Hong KongShenzhenShenzhen518172GuangdongChina Division of Decision and Control Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of Technology10044StockholmSweden Key Laboratory of Systems and Control Institute of Systems ScienceAcademy of Mathematics and System ScienceChinese Academy of SciencesBeijing100190China

Regularized system identification has become the research frontier of system identification in the past *** related core subject is to study the convergence properties of various hyper-parameter estimators as the sample size goes to *** this paper,we consider one commonly used hyper-parameter estimator,the empirical Bayes(EB).Its convergence in distribution has been studied,and the explicit expression of the covariance matrix of its limiting distribution has been ***,what we are truly interested in are factors contained in the covariance matrix of the EB hyper-parameter estimator,and then,the convergence of its covariance matrix to that of its limiting distribution is *** general,the convergence in distribution of a sequence of random variables does not necessarily guarantee the convergence of its covariance ***,the derivation of such convergence is a necessary complement to our theoretical analysis about factors that influence the convergence properties of the EB hyper-parameter *** this paper,we consider the regularized finite impulse response(FIR)model estimation with deterministic inputs,and show that the covariance matrix of the EB hyper-parameter estimator converges to that of its limiting ***,we run numerical simulations to demonstrate the efficacy of ourtheoretical results.

关键词： Regularized system identification Hyper-parameter estimator Empirical Bayes Convergence of covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Video Object Detection on Embedded Devices 13

Towards Efficient Video Object Detection on Embedded Devices

引用

13th International Conference on computer and Knowledge engineering, ICCKE 2023

作者： Hajizadeh, Mohammad Rahmani, Adel Sabokrou, Mohammad Iran University of Science and Technology School of Computer Engineering Tehran Iran Ipm Institute for Research in Fundamental Sciences School of Computer Science Tehran Iran

ISBN: (纸本)9798350330151

The challenge of adapting various object recognition techniques from still images to videos remains unsolved. When applied to videos, methods that are specifically designed for images do not perform well due to several complications. These include blurriness, shifting or ambiguous locations, subpar quality, and other similar concerns. In addition, a lack of effective long-term memory in video object detection has yet to be addressed. It is widely recognized that consecutive frames in a video tend to produce highly similar results in most cases. Therefore, this characteristic can be exploited to improve performance. Moreover, the information contained in a series of sequential or non-consecutive frames exceeds that of a single frame. In our research, we have introduced a novel recurrent cell for feature propagation and have determined the optimal layer placement to augment the memory span. This has resulted in superior precision compared to methods presented in previous research. Furthermore, hardware constraints may exacerbate this issue. Therefore, we have focused on implementing and improving the effectiveness of these techniques on embedded devices. Our approach has yielded impressive results, with a 67.5% mAP accuracy on the real-time ImageNet VID dataset for mobile devices at a rate of 62 fps. © 2023 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Implementing SLAM for Robot Navigation with Lidar in ROS Platform 4

Implementing SLAM for Robot Navigation with Lidar in ROS Pla...

引用

4th IEEE International Conference on Emerging Frontiers in Electrical and Electronic Technologies, ICEFEET 2024

作者： Verma, Gaurav Kumar Ray, Ranjit Swar, Surya Narayan Meena, Gagan Deep Dept. of Electrical Engineering National Institute of Technology Patna India Underwater Robotics & Autonomous Group CSIR-Central Mechanical Engineering Research Institute Durgapur India Department of Computer Science & Engineering Gandhi Institute of Engineering and Technology University Gunupur India

ISBN: (纸本)9798331528614

This research covers the implementation of SLAM (Simultaneous Localization and Mapping) with Ouster OS0 LiDAR (Light Detection and Ranging) sensor in the Robot Operating System (ROS1) Noetic. Using the high-frequency capabilities of the ouster, this method works towards mapping and localization in structured and unstructured environments. The paper explains the Ouster sensor integration in the ROS1 Noetic environment, providing information on the sensor calibration, data acquisition, and pre-processing. The ROS ecosystem in Ubuntu 20.04 is set to process the data streams coming from the ouster LiDAR sensor which is further utilised to create map and localize the robot. The Ouster LiDAR sensor scans every object in its field of view (in 3D), the data is then used for the SLAM. SLAM is executed using the Direct Lidar Odometry (DLO) algorithm for mapping and simultaneously helping the robot with localization and enabling it to navigate through the environment smoothly and precisely. © 2024 IEEE.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Implementation of Machine Learning and Ensemble Learning Techniques to Proactively Predict Students' Academic Success in the Realm of Higher Education 4

Implementation of Machine Learning and Ensemble Learning Tec...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Devkishan, Taneja Sanjay Singh, Sanjay Kumar Bharti, Ajay Kumar Amity Institute of Information Technology Amity University Uttar Pradesh Lucknow India United College of Engineering and Research Department of Computer Science and Engineering Prayagraj India

ISBN: (纸本)9798350387490

Predicting and analyzing student performance is a huge boon for both students and teachers. A number of analytical methodologies have been utilized in recent studies to forecast students' success;the CGPA is the end product of these analyses, which have been conducted for both the internal assessment as well as for the external assessment. Few well known machine learning algorithms have been suggested. Ensemble Learning along with Decision Trees, Support Vector Machine and Random Forest -obtained perfect 100s for Precision Value, Recall Value, as well as in F1 Scores in the evaluation of performances. Naive Bayes has worse performance in comparison, with F1 Scores of 66, Recall Value of 65, and Precision of 68. When contrasted with decision tree models, Support Vector Machines, Multi-Layer Perceptron, Ensemble Enabled Learning, and Random Forest, Naive Bayes, AdaBoost, and K-Nearest Neighbors all perform worse in terms of accuracy. The Naive Bayes classifier models the input distributions across classes and is very good in text categorization because it is a generative method. Since it fails to identify critical features for class differentiation, it cannot be distinguished from discriminative classifiers. © 2024 IEEE.

关键词： Adversarial machine learning

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：