检索结果-内蒙古大学图书馆

15th International Conference on Information and Communication technology Convergence, ICTC 2024

作者： Kasno, Mohammad Afif Yatim, Norhidayah Mohamad Kang, Tae-Won Hee, Jo Min Nam, JunWoo Jung, Jin-Woo Dongguk University Dept. of Computer Science and Egineering Seoul Korea Republic of Faculty of Electronics and Computer Technology and Engineering Malacca Malaysia Dongguk University Dept. of Artificial Intelligence Seoul Korea Republic of

ISBN: (纸本)9798350364637

This study presents a unique approach for operating the TurtleBot3 Waffle-Pi robot with voice instructions using the ROS Noetic framework. The system uses the SpeechRecognition library to translate voice inputs into movement commands, with the goal of improving user engagement and providing an intuitive control mechanism that can be applied to a variety of domains including assistive robotics. The system naturally interfaces with ROS Noetic, which uses Python for scripting and control logic. The method entails real-time recording audio with a microphone, filtering it to remove noise, then interpreting commands with Google's speech recognition API. For the TurtleBot3, commands like 'forward,' 'back,' 'left,' 'right,' and 'stop' are assigned to matching movements. Noise filtering and command disambiguation problems are solved by modifying the recognizer's energy threshold and using a dynamic energy threshold. A complete test was carried out in controlled situations to determine command recognition accuracy, response time, and navigation precision. The results showed good reliability and effectiveness, with accurate command recognition and minimum reaction delay. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Scrutinizing Domain-Specific Integrated Web Query Interfaces for Enhanced Security and Reliability in Storage Systems

Scrutinizing Domain-Specific Integrated Web Query Interfaces...

引用

2024 International Conference on Decision Aid sciences and Applications, DASA 2024

作者： Kumar, Rajeev Kumar, Pradeep Elngar, Ahmed A. Moradabad Institute of Technology Department of Computer Science and Engineering Uttar Pradesh Moradabad India Kuala Lumpur Malaysia Beni-Suef University Faculty of Computers and Artificial Intelligence Beni-Suef City62511 Egypt

ISBN: (纸本)9798350369106

In this paper, the module is designed to possess an assortment of unique and meticulously retrieved query interfaces from multiple representative domains like travel, entertainment, and living. Using Integrated Web Query Interfaces (IWQI), which are entirely built on VDIS (View-based data Integration System) and related to data from various data sources, we have presented a novel approach to online form integration. The essential processing of the proposed model starts from the wrapper module. This module is responsible for collecting data from various sources, extracting meaningful information from them, and identifying multiple web query interfaces. The proposed model follows and applies the rules that have been given and tested by researchers even before. In the given model two major mapping tasks have been done in the wrapper module. The organizational structure of all these elements in WQI along with the positional elements are also described and defined. © 2024 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Cooperative Multi-source data Trading

Cooperative Multi-source Data Trading

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Cheng, Jin Ding, Ningning Lui, John C. S. Huang, Jianwei The Chinese University of Hong Kong School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Hong Kong University of Science and Technology Data Science and Analytics Thrust Information Hub Guangzhou China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong The Chinese University of Hong Kong School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network Csijri Joint Research Centre on Smart Energy Storage Shenzhen China

ISBN: (纸本)9798350351255

In the era of big data, data trading significantly enhances data-driven technologies by facilitating data sharing. Despite the clear advantages often experienced by data users when incorporating multiple sources, the topic of multi-source data trading remains largely unexplored. This paper designs a novel data trading framework, which enables multi-source data trading through multi-source cooperation. The proposed framework aims to improve data usage efficiency and increase seller revenue. In particular, we model data sellers' cooperative decisions through the Nash bargaining framework and systematically outline the interactions between sellers and buyers as a two-stage Stackelberg game. A key contribution of this work is the consideration of coupling among diverse data products, which is essential but often overlooked in prior studies. We properly classify data's utility into endogenous and relational categories to disentangle the coupling. Despite the inherent non-convex nature of the optimization problem, we methodically derive the closed-form optimal solutions by decomposing the problem into several subproblems. Interestingly, we reveal that, under our proposed framework, sellers' revenue initially remains steady with the increase of product coupling level, but begins to rise once the level exceeds a certain threshold due to the substitute effect. Finally, experimental results show that our proposed framework can improve the seller's profit by up to 46.32% compared to traditional data trading methods in the current data market. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Intelligent Energy Harvesting from Biodegradable Waste Using Wireless Sensor Networks and Machine Learning Techniques 4

Intelligent Energy Harvesting from Biodegradable Waste Using...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Kannan, K. Jackulin Asha, G.S. Shobana, G. Sharanya, C. Beulah David, D. Sheeba Rani, S. R.M.K. College of Engineering and Technology Department of Electronics and Communication Engineering Puduvoyal Chennai India St.Joseph College of Engineering Department of Artificial Intelligence and Data Science Sriperumbudhur Chennai India Sri Krishna College of Engineering and Technology Department of Information Technology Coimbatore India Sathyabama Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Quantum Intelligence Chennai India Sri Eshwar Engineering College Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798331523923

Lack of electricity and the management of waste continue to be challenges in developing countries such as India. This project aims to provide a sustainable solution by utilizing food waste to generate electricity. The goal of the project is to maximize the energy generation from the waste by optimizing the arrangements and electrode combinations. After the electricity has been generated, it will be stored in the batteries. The monitoring system, which is called the node microcontroller, will also send data to the Think speak platform for analysis. This project's design considers the various factors that affect the quality of life in developing countries. It includes safety, scalability, and cost-effectiveness. By waste, the system can provide electricity to those who need it most. It is also contributing to the reduction of greenhouse gas emissions. © 2025 IEEE.

关键词： Things Speak

来源：评论

学校读者我要写书评

暂无评论

Implementation of Machine Learning Techniques for Predictive Security Analytics 12th

Implementation of Machine Learning Techniques for Predictive...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Moon, Pradnya S. Deshmukh, Anand B. Sarode, Harsha Jitendra Sharma, Shweta Birare, Komal Madhukar Anandpwar, Winit Nilkanth Department of Computer Technology Yashwantrao Chavan College of Engineering Maharashtra Nagpur India Department of Information Technology Sipna College of Engineering and Technology Maharashtra Amravati India Nutan Maharashtra Institute of Engineering and Technology Maharashtra Pune India Department of Artificial Intelligence and Data Science Arya College of Engineering Rajasthan Jaipur India Information Technology Vishwakarma Institute of Information Technology Maharashtra Pune India Department of Computer Science Dr. Ambedkar College Deekshabhoomi Maharashtra Nagpur India

ISBN: (纸本)9789819601462

Machine learning (ML)-based predictive security analytics has become an important part of modern defense. This study gives a brief overview of how machine learning can be used in predictive security analytics. Traditional security measures aren’t working as well as they used to because online risks are getting smarter and more complicated. We need to use proactive and predictive strategies instead. Machine learning systems can look through huge amounts of data and find trends and outliers that could mean an attack or security breach. Using controlled, unstructured, and reinforcement learning, predictive security analytics can spot problems early on and stop them before they become a real problem. Supervised learning algorithms, like support vector machines and neural networks, let security events be put into groups based on data that has already been named. This makes it easier to find threats. Unsupervised learning methods, like grouping and anomaly detection, make it easier to spot strange behavior that could be a sign of a security breach even without any training data. Because they learn from how they interact with their surroundings, reinforcement learning models let security systems change and get better over time. By adding machine learning models to security data tools, companies can improve their cyber defenses, which lets them proactively reduce threats and control risks. Furthermore, the ability of ML algorithms to learn new things all the time makes it possible for security measures to be flexible enough to react to changing dangerous environments. However, problems like bad data, models that are hard to understand, and threats from other people mean that ML for predictive security analytics needs to be carefully thought out and implemented using strong methods. © 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

Effective and Imperceptible Adversarial Textual Attack Via Multi-objectivization

引用

ACM Transactions on Evolutionary Learning and Optimization 2024年第3期4卷 1-23页

作者： Liu, Shengcai Lu, Ning Hong, Wenjing Qian, Chao Tang, Ke Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen College of Engineering South Tower 1088 Xueyuan Avenue Guangdong Shenzhen518055 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong999077 Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen 10F Zhizhen Building Canghai Campus 3688 Nanhai Avenue Guangdong Shenzhen China National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing University Nanjing International College Area Xianlin Campus 163 Xianlin Avenue Jiangsu Nanjing China

The field of adversarial textual attack has significantly grown over the past few years, where the commonly considered objective is to craft adversarial examples (AEs) that can successfully fool the target model. However, the imperceptibility of attacks, which is also essential for practical attackers, is often left out by previous studies. In consequence, the crafted AEs tend to have obvious structural and semantic differences from the original human-written text, making them easily perceptible. In this work, we advocate leveraging multi-objectivization to address such an issue. Specifically, we reformulate the problem of crafting AEs as a multi-objective optimization problem, where the attack imperceptibility is considered as an auxiliary objective. Then, we propose a simple yet effective evolutionary algorithm, dubbed HydraText, to solve this problem. HydraText can be effectively applied to both score-based and decision-based attack settings. Exhaustive experiments involving 44,237 instances demonstrate that HydraText consistently achieves competitive attack success rates and better attack imperceptibility than the recently proposed attack approaches. A human evaluation study also shows that the AEs crafted by HydraText are more indistinguishable from human-written text. Finally, these AEs exhibit good transferability and can bring notable robustness improvement to the target model by adversarial training. © 2024 Copyright held by the owner/author(s).

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

An Energy-Conscious and Delay-Aware Path Allocation for Emergency Node in WBAN 2nd

An Energy-Conscious and Delay-Aware Path Allocation for Emer...

引用

2nd International Conference on Intelligent Computing Systems and Applications, ICICSA 2023

作者： Menaga, S. Vanithamani, R. Anandkumar, A. Gomathi, N. Department of Electronics and Communication Engineering Jai Shriram Engineering College Tamil Nadu Tirupur India Department of Biomedical Instrumentation Engineering School of Engineering Avinashilingam Institute for Home Science and Higher Education for Women Tamil Nadu Coimbatore India Department of Artificial Intelligence and Data Science Karpagam Institute of Technology Tamil Nadu Coimbatore India

ISBN: (纸本)9789819754113

Wireless Body Area Network (WBAN) offer a viable solution for continuous health monitoring and are receiving a lot of attention from academicians and researchers due to recent technological advancements. In WBAN, sensors are placed throughout the body to collect physiological data and transmit it to a sink node. Thus, transmitting medical information between sensor nodes and sink nodes while consuming minimal energy, causing little packet loss, and extending the lifespan of the network is challenging. A linear regression buffalo optimization algorithm (LRBOA) for WBAN is introduced in this paper to enable the timely transmission of vital patient data. The linear regression method is used to identify normal, aberrant, and vital patient data in LRBOA. After the classification, the protocol schedules the priority for classified data. Within the specified timeframe, high-priority patient data can be transmitted first. Energy, link dependability, bandwidth, and distance-based optimal pathways are needed for data transfer. The suggested algorithm could determine the best path based on several variables, including energy, link dependability, bandwidth, and distance. The highest-priority node data is finally sent to the sink node for further processing. In this way, priority-based, energy-aware data transmission is performed in WBAN. The proposed algorithm is tested using a MATLAB with a health monitoring dataset in WBAN. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Linear Random Early Detection for Congestion Control at the Router Buffer

引用

Informatica (Slovenia) 2022年第5期46卷 105-114页

作者： Abu-Shareha, Ahmad Adel Al-Kasasbeh, Basil Shambour, Qusai Y. Abualhaj, Mosleh M. Alsharaiah, Mohmmad Abdalla Al-Khatib, Sumaya N. Department of Computer Science Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Riyadh Saudi Arabia Department of Software Engineering Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Networks and Information Security Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Data Science and Artificial Intelligence Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan

Active Queue Management (AQM) methods control the router's buffer to maintain high network performance and control congestion at the router buffer. Random Early Detection (RED) method is the most well-known and the most utilized AQM. RED suffers from a high dropping rate, which motivates the later AQM methods to use more complex processes, which reach the limits of using fuzzy systems as a processing technique. Yet, high computational cost affects the router's performance specifically and the network as a whole, with so-called processing delay. In this paper, a linear version of RED (LRED) is presented to reduce the computational cost of the original RED and maintain the network performance in terms of throughput, delay, dropping, and loss. LRED is built based on two distinctive features, simplifying the congestion indicator calculation and reducing the operations in calculating the dropping probability. The experimental results showed that the proposed method reduces the delay and the processing time while maintaining the throughput and loss of the RED method. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Network performance

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Prediction with Convolutional Neural Networks and Hyperparameter Tuning 8th

Cardiovascular Disease Prediction with Convolutional Neural ...

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Hossain, Mohammad Alamgir Metwally, Abdelnasser Abdelwakil Khan, Asif Ali Amin, Sherif Tawfik Hamdan, Alfadil Ahmed Limkar, Suresh Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department ofComputer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department ofComputer and Network Engineering College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of Artificial Intelligence & Data Science AISSMS Institute of Information Technology Maharashtra Pune India

ISBN: (纸本)9789819765805

CVD continues to pose a substantial global health burden, demanding the need for the creation of precise predictive models that can aid in the timely identification and evaluation of risks. This research paper aims to provide a thorough examination of the prediction of CVD by utilizing CNN in aggregation with hyperparameter tuning techniques. This paper examines the effectiveness of three widely recognized CNN architectures, namely ResNet, VGGNet, and Xception CVD. The Tree-structured Parzen Estimator (TPE) is utilized as a method for tuning hyperparameters in order to optimize the CNN models. The study commences with a comprehensive examination of the dataset, encompassing a wide array of cardiovascular CT image data. The chosen CNN architectures serve as the fundamental framework for our predictive models. The selection of these architectures is based on their established track record in effectively addressing image analysis tasks and their capacity to accurately capture complex patterns and features present in medical images. The models undergo training using a dataset in order to acquire knowledge about distinctive features that are linked to various cardiovascular conditions. The experimental findings presented in the study indicate that the utilization of the Xception architecture, in aggregation with TPE for hyperparameter optimization, yields the most favorable predictive accuracy. Specifically, the achieved accuracy rate of 98.26% is notably remarkable. This result highlights the significance of not only choosing advanced CNN architectures but also optimizing their hyperparameters to fully exploit their potential in predicting cardiovascular disease. This establishes it as a promising tool for the early diagnosis and risk assessment of CVD. This study establishes a fundamental basis for future investigations in the advancement of precise and dependable predictive models applicable to various medical imaging contexts. © The Author(s), under exclusive license

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Identification and Classification of Crowd Activities

引用

Computers, Materials & Continua 2022年第7期72卷 815-832页

作者： Manar Elshahawy Ahmed O.Aseeri Shaker El-Sappagh Hassan Soliman Mohammed Elmogy Mervat Abu-Elkheir Department of Information Technology Faculty of Computers and InformationMansoura UniversityEgypt Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Information Systems Faculty of Computers and Artificial IntelligenceBenha UniversityEgypt Faculty of Computer Science and Engineering Galala University435611SuezEgypt Department of Computer Science Faculty of Media Engineering and TechnologyGerman UniversityEgypt

The identification and classification of collective people’s activities are gaining momentum as significant themes in machine learning,with many potential applications *** need for representation of collective human behavior is especially crucial in applications such as assessing security conditions and preventing crowd *** paper investigates the capability of deep neural network(DNN)algorithms to achieve our carefully engineered pipeline for crowd *** includes three principal stages that cover crowd analysis ***,individual’s detection is represented using the You Only Look Once(YOLO)model for human detection and Kalman filter for multiple human tracking;Second,the density map and crowd counting of a certain location are generated using bounding boxes from a human detector;and Finally,in order to classify normal or abnormal crowds,individual activities are identified with pose *** proposed system successfully achieves designing an effective collective representation of the crowd given the individuals in addition to introducing a significant change of crowd in terms of activities *** results onMOT20 and SDHA datasets demonstrate that the proposed system is robust and *** framework achieves an improved performance of recognition and detection peoplewith a mean average precision of 99.0%,a real-time speed of 0.6ms non-maximumsuppression(NMS)per image for the SDHAdataset,and 95.3%mean average precision for MOT20 with 1.5ms NMS per image.

关键词： Crowd analysis individual detection You Only Look Once(YOLO) multiple object tracking kalman filter pose estimation

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：