检索结果-内蒙古大学图书馆

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

Comparative Analysis of Infant Cry Classification using Machine Learning and Deep Learning Techniques 1

Comparative Analysis of Infant Cry Classification using Mach...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Ramulu, Kothuri Parashu Jogannagari, Pranathi Reddy Indur Institute of Engineeing & Technology Department of Computer Science and Engineering Siddipet India University of Alabama at Birmingham Department of Computer Science Birmingham United States

ISBN: (纸本)9798331529246

Infant Cry Classification is the process of analyzing acoustic signals from an infant's cry for extracting relevant features to determine the cause of crying, and assess the infant's health condition. The process is typically divided into four main stages: pre-processing, feature extraction, feature fusion, and classification. In the feature extraction stage, spectrograms along with frequency transforms such as the Wavelet Transform, Cosine Transform, and Fourier Transforms are employed to capture important characteristics of the cry. The feature fusion stage is critical as it integrates information from various scales and contexts obtained during feature extraction, allowing for a more comprehensive representation of the cry's features. In current times, both Machine Learning (ML) and Deep Learning (DL) techniques are employed for classification. The ML techniques predominantly utilized in this process are: Multi-Class Support Vector Machines (SVM), Hyperparameter-Optimized SVM, Kernel-based SVM, Ensemble Boosting methods, Random Forest classifiers, K-Nearest Neighbors (K-NN), and Bayesian Optimization. In the case of DL architectures, models such as Style and Latent Guided Adversarial Networks (SLGAN), Multi-Layer Perceptron (MLP), Convolutional Neural Network - Sparse Convolution Net (CNN-SCNet), 1D CNN, and Dual-CNN are frequently employed to ensure high accuracy. The performance of these classification algorithms is evaluated in terms of the following metrics: sensitivity, specificity, accuracy, precision, and F-measure. © 2025 IEEE.

关键词： Cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Applications of Machine Learning in Cloud Forensics

Applications of Machine Learning in Cloud Forensics

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Theertani, Malluri Reddy Valeti, Neha Solanki, Darshini Kumar, Kakelli Anil Vellore Institute of Technology Vellore Computer Science and Engineering Vellore India Vellore Institute of Technology Vellore Sr. School of Computer Science Engineering Vellore India

ISBN: (纸本)9798350333602

Cloud computing has recently experienced rapid expansion, making it a major target for cybercrimes. Though cloud computing has many advantages, there are also substantial security issues related to confidentiality, integrity, privacy, and availability. Being a relatively new discipline, cloud forensics faces numerous challenges and issues with interpreting and analyzing data. Forensic investigators and law enforcement confront numerous difficulties in data collection, data protection, and evidence access. Several sophisticated models have been proposed in recent years aiming to accelerate the entire investigation process or address several issues that arise frequently in forensic investigations. This review paper seeks to comprehend the significance of various machine learning models which would help cloud forensics advance significantly. It also provides a detail information on cloud forensics as well as the research trends that have been going on in this field over the past few years. A detailed comparative analysis of different approaches of machine learning on development of cloud forensics has been presented in this research study. © 2023 IEEE.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis for Depression Detection Using Artificial Intelligence 3

Sentiment Analysis for Depression Detection Using Artificial...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Choudhary, Dilip Kumar Gupta, Anisha Singh, Sriaum Abhinav, Tejashvi Agrawal, Tanvi Vellore Institute of Technology School of Electronics Engineering Vellore632014 India Vellore Institute of Technology School of Computer Science and Engineering Vellore632014 India

ISBN: (纸本)9798350372120

Depression, a leading mental health concern, affects millions globally. Early detection remains crucial for effective intervention. This study explores the potential of sentiment analysis, powered by Artificial Intelligence (AI), for depression detection. We analyse existing research, examining data sources, feature extraction techniques, and AI-based methodologies. We then conduct a preliminary review of existing AI-based depression detection systems, highlighting their strengths and limitations. Our findings indicate promising applications of sentiment analysis in identifying individuals at risk of depression. However, further research is necessary to address challenges related to data privacy and the need for robust and standardized methodologies. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Tensorial Evolutionary Computation for Spatial Optimization Problems

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 154-166页

作者： Si-Chao, Lei Xiaolin, Xiao Yue-Jiao, Gong Yun, Li Jun, Zhang the School of Computer Science and Engineering South China University of Technology Guangzhou510006 China the Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen610056 China the School of Computer Science South China Normal University Guangzhou510006 China the Department of Electrical and Electronic Engineering Hanyang University Seoul15588 Korea Republic of

—Spatial optimization problems (SOPs) refer to a class of problems where the decision variables require spatial organization. Existing methods based on evolutionary algorithms (EAs) fit conventional evolutionary operators by flattening the spatial representations of SOPs to one dimension, which hence loses crucial spatial structures of the potential solutions. To address this issue, this article proposes a tensorial evolutionary algorithm (TEA) by formulating a tensor space of the SOPs, where the population of candidate solutions is represented as a third-order tensor. Accordingly, we design a tensor-product crossover operator and a two-phase mutation consisting of a local convolutional mutation operator and a global Gaussian mutation operator in the tensor space. These operators are all implemented based on tensor operations. Under the consideration of spatial context on individual solutions, we devise three types of evolutionary tensors, namely, the crossover tensor, the convolutional mutant tensor, and the Gaussian mutant tensor for the three tensorial evolutionary operators correspondingly. The resultant TEA is tested using two typical real-world SOPs, namely, the facility layout problem and the image steganography problem. Comparative experimental studies validate the effectiveness and robustness of TEA. © 2024 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Static and Dynamic Routing Protocols in Network Security Attacks 4

Static and Dynamic Routing Protocols in Network Security Att...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Abrol, Lovedeep Gahelot, Parul Chitkara University Institute of Engineering and Technology Computer Science and Engineering Punjab India

ISBN: (纸本)9798350300888

Network devices use communication protocols to transfer information by physical or wireless technologies, including routers and access points. Networking components are used to software monitor, manage and secure the network. The router is quite trained by the use of reinforcement learning which can make all the hardest decisions for making algorithms. Routing selects Internet Protocol(IP) paths, also known as Internet Protocol, and those packages are sent from their starting point. Routers can make the decision to route packets along with the network paths. An innovative routing system for Flying AdHoc Network(FANET) is provided by an enhanced form of AntHocNet. Dynamic routing protocols are more efficient in medium and large networks because they require most of the computing power, which is why smaller networks rely on the static routing protocol. In this study, routing algorithms, dynamic routing networks, Unmanned Aerial Vehicle(UAV) protocol, Routing Protocol(RPL) in the security of networks, and Flying Ad hoc networks are discussed. © 2023 IEEE.

关键词： Wireless sensor networks

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

Analysis and Prediction of COVID-19 Disease using Machine Learning 14

Analysis and Prediction of COVID-19 Disease using Machine Le...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Parmar, Shabnam Rani, Rinkle Kalra, Nidhi Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Patiala India

In this research, the symptoms and other factors of a patient are utilized to train machine learning algorithms to predict whether the patient would die from or recover from (COVID19). It is probable that the coronavirus (COVID19) will create the highly infectious Coronavirus illness COVID19 (SARSCoV2). By coughing, sneezing, speaking, or inhaling, this virus can be transmitted from an infected person's lips and nose to small liquid particles. The size of these tiny atoms' inhalation droplets and aerosols vary, with bigger droplets being larger than smaller atoms. COVID19 is transferred by inhalation or by touching your eyes, nose, or mouth with your fingers after meeting a contaminated surface. When a big number of people are present, the COVID-19 virus can spread rapidly. We will need to examine the COVID19 dataset to see which models are the most accurate in estimating fatality rates for the virus's most vulnerable victims. Machine learning is used to compute and evaluate the performance of a variety of prediction models. We have used K-nearest neighbor (KNN), Support Vector Machine (SVM) classifier, Gaussian naive Bayesian (GNB), Decision tree (DT), and Logistic regression (LR) for the prediction of death and recovery of symptomatic patients. In this research, a variety of feature selection and extraction strategies were used, and prediction accuracy for feature selection methods for the KNN model and feature extraction methods for the GNB model both reached up to 96 percent. The k-nearest neighbor has performed and predicted high accuracy of 96% in both feature selection and extraction techniques. © Grenze Scientific Society, 2023.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Face Recognition Based on Cascade Classifier Using Deep Learning 1

Face Recognition Based on Cascade Classifier Using Deep Lear...

引用

1st IEEE International Conference on Innovations in High Speed Communication and Signal Processing, IHCSP 2023

作者： Mannepalli, Praveen Kumar Singh Kushwaha, Devendra Kalamdhar, Sanjay Nagrale, Vishakha Rajpoot, Vikram GH Raisoni Institute of Engineering and Technology Department of Computer Science & Engineering Nagpur India Madhav Institute of Technology & Science Gwalior India

ISBN: (纸本)9798350345957

The human face is significant because it is used as a tool of identification in our daily lives. One kind of biometric identification is Face Recognition (FR), which works by memorizing and using a person's unique facial features to identify that person in the future. Numerous researchers have been interested in biometric facial recognition technology due to its widespread use. Because of the non-contact nature of the process, FR technology surpasses other biometric-based authentication methods like fingerprint, palm print, & iris recognition. One such potential use for facial recognition (FR) algorithms is in remote identification when no physical touch or interaction with the target individual is required. This study proposes a method for constructing an FR system with a learning strategy depending on the DCNN algorithm. The approach of Deep Learning (DL) is presented for learning & assessing all samples & new inputs in a scheme. The ORL and YALE face datasets are used in studies that compare the findings to those produced by the Deep CNN approach. The proposed DL method uses a systematic approach to learning from and assessing new inputs and samples. The proposed model Deep CNN obtained 96.04 percentage points (or a validation accuracy of 62.2%) over the ORL dataset after 100 iterations with a loss of 17.33 percent. DCNN achieves a 99.99% training accuracy and a 99.89% validation accuracy without any data loss after 100 epochs of training on the Extended Yale B dataset. The proposed DL method analyses and rates are existing data from the system and fresh face inputs. In addition, it gathers information from the facial features & enhances the D-CNN algorithm for facial classification. Utilizing CNN (Convolutional Neural Networks), the accomplishments in several contests are advancing and becoming the focus of study. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Smart City Surveillance: Survey on Current Status and Future Trends 14

Smart City Surveillance: Survey on Current Status and Future...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Neyaz, Hera Paul, Hrituparna Srivastava, Anima Singh, Shiksha Dept. of Computer Science and Engineering Shambhunath Institute of Engineering and Technology India

This paper presents a comprehensive survey on surveillance and security aspects of a smart city. Multiple dimensions of a smart city surveillance system have been discussed. The current trends and methodologies are thoroughly researched and presented. The algorithms of novel methods are reviewed along with analytics and methodologies. Impact of XAI in the smart city surveillance is discussed. Advantages and disadvantages of current infrastructures have been included in the broad literature survey. Lastly, the challenges and future trends are conferred to. © Grenze Scientific Society, 2023.

关键词： Smart city

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：