检索结果-内蒙古大学图书馆

6th International Conference on Intelligent computing and Signal Processing (ICSP)

作者： Hang Zhang Yuhui Li Shijian Kui Zhaoyi Qin Faculty of Computing Harbin Institute of Technology Harbin China School of Automotive Engineering Harbin Institute of Technology Harbin China Faculty of New Energy Harbin Institute of Technology Harbin China School of Information Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

With the rapid development of deep learning technology, deep counterfeiting has also quietly ascended to the stage of history, and voice disguise fraud, as a new type of attack means, has laid a huge hidden danger for people's privacy security. Based on the research of speech synthesis, this paper designs and implements a speech disguise synthesis system based on the Tacotron2 model, and uses the WaveGlow model as a vocoder to replace the original WaveNet module, which is used to simulate experimental research from the direction of the attack to achieve a better synthesis effect. After this experiment, this paper verifies the feasibility of the program and provides technical references for subsequent security technology development.

关键词： Training Attention mechanisms Vocoders Semantics Syntactics Real-time systems Acoustics Fraud Speech synthesis Security

来源：评论

学校读者我要写书评

暂无评论

Precise Prediction of Cardiovascular Diseases Using Machine Learning 2

Precise Prediction of Cardiovascular Diseases Using Machine ...

引用

2nd International Conference on Smart Technologies and Systems for Next Generation computing, ICSTSN 2023

作者： Revathy, G. Venkateswaran, S. Senthil Murugan, V. Devi, V. Mohanadevi, A. Saravanan, G. Sastra Deemed University School of Computing Thanjavur India Veltech Rangarajan Dr Sagunthala R&d Institute of Science and Technology Department of Cse Chennai India Mohan Babu University School of Computing Tirupathi India Thiruthangal Nadar College Department of Computer Science Chennai India Saranathan College of Engineering Department of Cs & Bs Trichy India Erode Sengunthar Engineering College Department of Aids Erode India

ISBN: (纸本)9798350348002

Cardiovascular disease is among the conditions that pose the greatest risk to life. Nearly 17 million people die as a result of its high mortality rate worldwide. To treat the illness quickly and reduce mortality, early diagnosis is helpful. The occurrence and absenteeism of the ailment can be hush-hush consuming a variability of ML techniques. The UCI dataset is to categorize heart disease using the techniques of LR, NB,SVM and Convolution Neural Networks(CNN). To progress the model's recital, the dataset was cleaned, missing value searches were carried out, and feature selection was done through correlation by the goal worth for all of the features. The traits with the highest favourable associations were picked. The dataset is then alienated into train and trial sets, and classification is completed experimenting with a 70:30:80 ratio. The most accurate dividing ratio is 80:20. The best outcome will be recorded and used in the suggested model, which will compare Logistic regression, Naive Bayes, and Support vector machines with and without feature selection. Among all the models CNN shows the best result. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Multi Cancer Prediction using Deep Learning and CNN Algorithm

Multi Cancer Prediction using Deep Learning and CNN Algorith...

引用

International Conference on Inventive computing and Informatics (ICICI)

作者： Siddharth Patel Zayd Hassan S. Iniyan Usha Desai Department of Computer Science and Engineering SRM Institute of Science and Technology Kaatankulathur Chennai Tamilnadu India Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kaatankulathur Chennai Tamilnadu India S. E. A. College of Engineering & Technology Bengaluru

ISBN: (数字)9798350373295

ISBN: (纸本)9798350373301

Deep learning approach is used to predict the chance of acquiring several types of malignancies, including breast, brain, lung, colon, oral, kidney, and cervical cancer. To find patterns and risk factors linked to each kind of cancer, deep learning algorithms, such as convolutional neural networks and recurrent neural networks, are trained on enormous databases of patient data, including genetic markers, lifestyle variables, and medical history. Deep learning algorithms can accurately forecast an individual’s risk of acquiring cervical, lung, colon, oral, kidney, breast, or brain cancer by evaluating these intricate datasets. Results indicate varied performance across cancer types, with cervical, breast, lung, and colon cancer models exhibiting high accuracy (>98%) and lower validation losses, suggesting strong generalization capabilities. Conversely, kidney and oral cancer models displayed signs of overfitting, emphasizing the challenges of model generalization. These findings highlights the DL’s potential in enhancing cancer detection, early diagnosis, and personalized treatment planning.

关键词： Deep learning Prevention and mitigation Lung Breast Prediction algorithms Brain modeling History

来源：评论

学校读者我要写书评

暂无评论

Optimization of Lightning Protection System Using Multi-Objective Optimization Techniques 37

Optimization of Lightning Protection System Using Multi-Obje...

引用

37th International Conference on Lightning Protection, ICLP 2024

作者： Tang, Jia-Wen Wooi, Chin-Leong Tan, Wen-Shan Cooray, Vernon Kadir, Mohd Zainal Abidin Ab Afrouzi, Hadi Nabipour Faculty of Electrical Engineering Technology Universiti Malaysia Perlis Pauh Putra Campus Perlis Arau02600 Malaysia Faculty of Electrical Engineering Technology Universiti Malaysia Perlis Pauh Putra Campus Perlis Arau02600 Malaysia School of Engineering and Advance Engineering Platform Monash University Malaysia Jalan Lagoon Selatan Selangor Bandar Sunway47500 Malaysia Department of Electrical Engineerin Uppsala University Uppsala Sweden Faculty of Engineering Universiti Putra Malaysia Selangor Seri Kembangan Malaysia Faculty of Engineering Computing and Science Swinburne University of Technology Sarawak Sarawak Kuching93350 Malaysia

ISBN: (纸本)9783800764174

This study aims to enhance the reliability of an 80-line distribution system against lightning strikes by minimizing interruptions and associated costs. ATPDraw transient models simulate Lightning Protection System (LPS) configurations such as feeder shielding and grounding, to obtain critical lightning currents for estimating fault rates due to lightning strikes. Employing and comparing the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) with the Multi-Objective Particle Swarm Optimization (MOPSO), the optimization model integrates diverse LPS configurations into the distribution network. The optimal LPS configurations are determined with the minimum System Average Interruption Frequency Index (SAIFI), the Momentary Average Interruption Frequency Index (MAIFI) and associated costs. The study identifies specific grounding rod configurations, reducing SAIFI from 4.52 int./yr. to 3.47 int./yr. and MAIFI from 22.58 int./yr. to 17.33 int./yr. Validation under various cost constraints reveals a direct relationship between investment and system reliability. NSGA-II proves more effective in optimizing grounding systems and shielding measures compared to MOPSO, highlighting the significance of optimized lightning protection strategies for system resilience, cost-effectiveness, and regulatory compliance in power distribution networks. © 2024 IEEE, © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Transforming Greenhouse Horticulture Using Artificial Intelligence and Digital Twin

Transforming Greenhouse Horticulture Using Artificial Intell...

引用

2023 IEEE International Conference on Quantum Technologies, Communications, computing, Hardware and Embedded Systems Security, iQ-CCHESS 2023

作者： Joshi, Kapil Gupta, Ashulekha Rawat, Amar Jeet Kumar, Rajiv Gupta, Omdeep Uttaranchal Institute of Technology Uttaranchal University Department of Cse Dehradun India Department of Management Studies Dehradun India Uttaranchal University Uttaranchal School of Computing Sciences Dehradun India Shivalik College of Engineering Computer Science and Engineering Department Dehradun India Graphic Era Hill University School of Management Dehradun India

ISBN: (纸本)9798350314946

In todays, to cope with the problems caused by the rising worldwide need for basic foodstuffs, it is vital to discover ecologically friendly solutions. Vegetable crops may be grown all year long, regardless of the climate or season, thanks to horticulture. The production process for horticulture may be categorized as an unstructured & extremely complicated system that is influenced by the climate, environment, pests, disease, herbicides, nutrients, pricing, & combinations of these numerous aspects. Digital twins might be seen as the beginning of a new era in data-driven & intelligent greenhouse horticulture. The study of the article is about the advancement of horticulture via the application of reducing technologies, especially digital technology. The purpose of this article is to offer, with the need for technology, the vital information that producers may utilize to harvest a range of crops to reap the most rewards. This study describes the outcomes of structured use of the Digital Twin application throughout greenhouse horticulture, as Artificial Intelligence applies to learn approaches throughout its applications to proclaim the best cost-effective & maximal benefit for the agriculturist. Based on the analysis, the article identifies challenges and suggests a few vital recommendations for future work. The findings of this study on the efficiency of concept in the growth of concentrated fruits and vegetables are examined. © 2023 IEEE.

关键词： Horticulture

来源：评论

学校读者我要写书评

暂无评论

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors 39

NumbOD: A Spatial-Frequency Fusion Attack Against Object Det...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhou, Ziqi Li, Bowen Song, Yufei Yu, Zhifei Hu, Shengshan Wan, Wei Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

ISBN: (纸本)157735897X

With the advancement of deep learning, object detectors (ODs) with various architectures have achieved significant success in complex scenarios like autonomous driving. Previous adversarial attacks against ODs have been focused on designing customized attacks targeting their specific structures (e.g., NMS and RPN), yielding some results but simultaneously constraining their scalability. Moreover, most efforts against ODs stem from image-level attacks originally designed for classification tasks, resulting in redundant computations and disturbances in object-irrelevant areas (e.g., background). Consequently, how to design a model-agnostic efficient attack to comprehensively evaluate the vulnerabilities of ODs remains challenging and unresolved. In this paper, we propose NumbOD, a brand-new spatial-frequency fusion attack against various ODs, aimed at disrupting object detection within images. We directly leverage the features output by the OD without relying on its internal structures to craft adversarial examples. Specifically, we first design a dual-track attack target selection strategy to select high-quality bounding boxes from OD outputs for targeting. Subsequently, we employ directional perturbations to shift and compress predicted boxes and change classification results to deceive ODs. Additionally, we focus on manipulating the high-frequency components of images to confuse ODs’ attention on critical objects, thereby enhancing the attack efficiency. Our extensive experiments on nine ODs and two datasets show that NumbOD achieves powerful attack performance and high stealthiness. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Cooperative Trajectory Tracking Control of Multiple Mobile Robots Under Motor Voltage Losses

Cooperative Trajectory Tracking Control of Multiple Mobile R...

引用

Control Conference (ANZCC), Australian and New Zealand

作者： Zhao-Qing Liu Xiaohua Ge Hao Xie Qing-Long Han Jinchuan Zheng Xian-Ming Zhang School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne VIC Australia Shanghai Aerospace Control Technology Institute Shanghai China School of Automation Science and Electrical Engineering Beihang University Beijing China

This paper deals with the cooperative trajectory tracking (CTT) control problem of multiple mobile robot (MR) systems subject to motor voltage losses. To account for the adverse effect induced by motor voltage loss, the dc-motor dynamics are first introduced in the multiple MR system (multi-MRS). Then, to guarantee the successful completion of CTT missions even in the presence of motor voltage loss, unknown dynamics, and external disturbances, a resilient adaptive CTT control design approach, including the design of a virtual kinematic control law, a virtual current control law as well as a voltage control law, is developed. In addition, a CTT error dynamics is derived for multi-MRSs by incorporating the simultaneous effects of motor voltage loss, unknown dynamics, and external disturbances. After that, a formal theoretical analysis of the stability for the derived CTT error dynamics is provided. At last, an experimental example study is provided to substantiate the efficacy of the developed resilient adaptive CTT control design approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Metamaterial-Based MM-Wave Phased Array for Broadband Cellular Networks

Metamaterial-Based MM-Wave Phased Array for Broadband Cellul...

引用

2023 International Telecommunications Conference, ITC-Egypt 2023

作者： Amar, Ahmed S.I. Parchin, Naser Ojaroudi Fawzy, Diaa E. Allam, A.M.M.A. Eid, Alaa M. Soliman, Mohamed A. Alexandria University Air Defense College Department of Electronics and Communication Alexandria Egypt Edinburgh Napier University School of Computing Engineering and the Built Environment Edinburgh United Kingdom Izmir University of Economics Faculty of Engineering Izmir Turkey German University in Cairo Faculty of Information and Engineering Technology Cairo Egypt

ISBN: (纸本)9798350326062

A new broadband phased array antenna with wide-scan and high-gain beam-scanning are desirable to meet the requirements of future cellular networks. This paper discusses the characteristics of a new beam-steerable array design having broad bandwidth for 5G communications. The discussion is focused on smartphones, due to their small size and complexity. The design procedure is straightforward and accomplished on a mainboard of future smart handheld devices. The introduced phased array design involves eight metamaterial-based dipole resonators with a 1×8 linear form. The resonators have small sizes with microstripline feedings. For -10 dB, the design represents 28-38 GHz covering several bands in the 5G spectra. © 2023 IEEE.

关键词： Resonators

来源：评论

学校读者我要写书评

暂无评论

Clause-level Relationship-aware Math Word Problems Solver

引用

Machine Intelligence Research 2022年第5期19卷 425-438页

作者： Chang-Yang Wu Xin Lin Zhen-Ya Huang Yu Yin Jia-Yu Liu Qi Liu Gang Zhou Anhui Province Key Laboratory of Big Data Analysis and Application School of Data ScienceUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Laboratory of Mathematical Engineering and Advanced Computing Information Engineering UniversityZhengzhou 450001China

Automatically solving math word problems,which involves comprehension,cognition,and reasoning,is a crucial issue in artificial intelligence *** math word problem solvers mainly work on word-level relationship extraction and the generation of expression solutions while lacking consideration of the clause-level *** this end,inspired by the theory of two levels of process in comprehension,we propose a novel clause-level relationship-aware math solver(CLRSolver)to mimic the process of human comprehension from lower level to higher ***,in the lower-level processes,we split problems into clauses according to their natural division and learn their *** the higher-level processes,following human′s multi-view understanding of clause-level relationships,we first apply a CNN-based module to learn the dependency relationships between clauses from word relevance in a local ***,we propose two novel relationship-aware mechanisms to learn dependency relationships from the clause semantics in a global ***,we enhance the representation of clauses based on the learned clause-level dependency *** expression generation,we develop a tree-based decoder to generate the mathematical *** conduct extensive experiments on two datasets,where the results demonstrate the superiority of our framework.

关键词： Artificial intelligence(AI) artificial neural network(ANN) computational mathematics machine intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

Recommendation System using Inference-based Graph Learning - Modeling and Analysis 2

Recommendation System using Inference-based Graph Learning -...

引用

2nd International Conference on Innovative Sustainable Computational Technologies, CISCT 2022

作者： Bhaskaran, S. Hariharan, S. Veeramanickam, M.R.M. Bharathiraja, N. Pradeepa, K. Marappan, Raja Sastra Deemed University School of Computing Thanjavur India Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India St. Michael College of Engineering and Technology Department of Computer Science and Engineering India

ISBN: (纸本)9781665474160

Recently, the development of recommendation systems has been an emerging area where the target is the learner's preferences, and styles should be learned from past interactions to predict the ratings and recommendations of the new items. The significant critiques and challenges are some of the datasets are sparse and the bias in the ratings and popularity of the items that conventional recommenders can't efficiently process. This research constructs the graph model to merge the items and user interaction to enhance user representations. The new inference operator is designed to remove the bias factors and to draw inferences. The users and items are represented with high quality by constructing the semantic space that connects the users and the item's characteristics. The proposed model is simulated on real-world datasets, proving that the model produces significant outcomes better than existing methods. © 2022 IEEE.

关键词： Recommender systems

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：