检索结果-内蒙古大学图书馆

Linguistic feature template integration for Chinese-Vietnamese neural machine translation

Frontiers of Computer science 2022年第4期16卷 223-225页

作者： Zhiqiang YU Yantuan XIAN Zhengtao YU Yuxin HUANG Junjun GUO Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China School of Mathematics and Computer Science Yunnan Minzu UniversityKunming 650500China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650500China

1 Introduction and main contributions Template-based approaches have achieved significant progress in low-resource neural machine translation(NMT)recently[1],such as the efficient works,NMT-GTM[2],SoftPrototype[3],***,most previous works only retrieve target sentence as template to generate translation,neglecting the utilization of linguistic feature that contained in the source sentence and template.

关键词： translation template such

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Prediction by Incorporating Bio-inspired Optimization in Deep Neural Network

引用

SN Computer science 2024年第8期5卷 1-20页

作者： Mundada, Monica R. Sowmya, B.J. Supreeth, S. Prabhu, Smitha G. Mahesh, K. Vishwanath, Y. Rohith, S. Department of Computer Science and Engineering M S Ramaiah Institute of Technology Bengaluru 560054 India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru 560054 India School of Computer Science and Engineering REVA University Bengaluru 560064 India Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru India Department of Electrical and Electronics Engineering Sir M Visvesvaraya Institute of Technology Bengaluru India School of Computer Science & Engineering Presidency University Bengaluru 560064 India Department of Electronics & Communication Engineering Nagarjuna College of Engineering & Technology Bengaluru 562164 India

This study offers a unified surgical conception of skin neoplasms using deep learning and genetic optimization techniques to improve classification values and speed of diagnosis. In this case, the architecture of Convolutional Neural Networks such as MobileNet, Xception and Inception is enhanced on the basis of the creative algorithms of Particle Swarm Optimization and Bat Algorithm to adjust the hyperparameters. The Heroku hosted cloud solution permits registered users to upload pictures of skin lesions via the web interface, where the picture is then processed through a Deep Neural Network (DNN) model that classifies the lesion as either melanoma or non-melanoma. The Convolution Neural Network (CNN) models were trained and evaluated on large publicly available datasets of skin lesions like ISIC, HAM10000 and the model performance was evaluated based on the effect of varying optimizers. Among all the architectures, Xception with Bat Algorithm (BA) performed best because of the more complex and deeper network architecture and extreme inception modules, which made it possible to extract and classify more complicated features. As a cloud-based solution, this system provides dermatologists and health practitioners with a more practical and workable solution for the detection of skin cancers. Furthermore, it can be utilized in other fields, which implies that this approach could extend its applications beyond dermatological imaging or imaging of patients at risk for other diseases, thus creating an adaptable and effective tool for clinical diagnosis in many areas of medicine. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Bio-inspired optimization Deep neural network (DNN) Skin cancer prediction

来源：评论

学校读者我要写书评

暂无评论

Voice-Controlled Navigation for TurtleBot3 using ROS Noetic and Speech Recognition 15

Voice-Controlled Navigation for TurtleBot3 using ROS Noetic ...

引用

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

Energy Requirement and Availability Analysis in the Indian Subcontinent using Machine Learning 9

Energy Requirement and Availability Analysis in the Indian S...

引用

9th IEEE International Conference for Convergence in technology, I2CT 2024

作者： Annadate, Prutha Annadate, Mrunal Dr. Vishwanath Karad Mit World Peace University School of Computer Engineering And Technology - Artificial Intelligence And Data Science Pune India Dr. Vishwanath Karad Mit World Peace University School of Electronics And Communication Engineering Pune India

ISBN: (纸本)9798350394474

Efficient energy data analysis and then prediction can be especially beneficial in the Indian Subcontinent with its ever-growing need and industrial expansion. The authors developed and compared three different machine learning (ML) models namely, Linear Regression, Decision Tree Regression and Random Forest Regressor for energy requirement against energy availability analysis restricted to the mentioned region. The models achieved an R2 value of 99.76%, 99.58% and 99.72% respectively. Observations regarding the results obtained were discussed along with a review of related works. Finally, the authors provided some pointers for future research. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Retroflex: Uncovering Visual Equivalences through Reverse Image Recon

Retroflex: Uncovering Visual Equivalences through Reverse Im...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Sneha M. Yadav Karik Shailendra Joshi Divyah Tarun Mandavia Parth Mahendra Puri Dept. Artificial Intelligence and Data Science Vidyavardhini’s College of Engineering and Technology Mumbai India

This research introduces a comprehensive method for Reverse Image Search (RIS) this can be also called as CBIR that is Content Based Image Retrieval designed for large datasets with more than 50,000 photos in 25 different classes. The approach uses sophisticated deep learning feature extraction methods, such as Auto-encoders and CNNs, to extract complex visual representations for reliable content characterization. We incorporate advanced indexing techniques to address the issues of scalability and retrieval efficiency. The resultant framework exhibits higher accuracy and speed and provides an optimal and sophisticated solution for picture retrieval problems. This effort is a major step forward in improving the capabilities of RIS systems, offering a flexible tool for real-world applications that need for thorough and effective image retrieval across a range of classes.

关键词：

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

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

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

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

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

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：