检索结果-内蒙古大学图书馆

Data Augmentation and Random Multi-Model Deep Learning for Data Classification

computers, Materials & Continua 2023年第3期74卷 5191-5207页

作者： Fatma Harby Adel Thaljaoui Durre Nayab Suliman Aladhadh Salim EL Khediri Rehan Ullah Khan Computer Science Department Future Academy-Higher Future Institute for Specialized Technological StudiesEgypt Department of Computer Systems Engineering Faculty of Electrical and Computer EngineeringUniversity of Engineering and TechnologyPeshawar25120Pakistan Department of Information Technology College of ComputerQassim UniversityBuraydahSaudi Arabia Department of Computer Sciences Faculty of Sciences of GafsaUniversity of GafsaGafsaTunisia

In the machine learning(ML)paradigm,data augmentation serves as a regularization approach for creating ML *** increase in the diversification of training samples increases the generalization capabilities,which enhances the prediction performance of classifiers when tested on unseen *** learning(DL)models have a lot of parameters,and they frequently ***,to avoid overfitting,data plays a major role to augment the latest improvements in ***,reliable data collection is a major limiting ***,this problem is undertaken by combining augmentation of data,transfer learning,dropout,and methods of normalization in *** this paper,we introduce the application of data augmentation in the field of image classification using Random Multi-model Deep Learning(RMDL)which uses the association approaches of multi-DL to yield random models for *** present a methodology for using Generative Adversarial Networks(GANs)to generate images for data *** experiments,we discover that samples generated by GANs when fed into RMDL improve both accuracy and model *** across both MNIST and CIAFAR-10 datasets show that,error rate with proposed approach has been decreased with different random models.

关键词： Data augmentation generative adversarial networks classification machine learning random multi-model deep learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating Machine Learning Algorithms for Early Detection of GDM 6

Evaluating Machine Learning Algorithms for Early Detection o...

引用

6th International Congress on Human-computer Interaction, Optimization and Robotic Applications, HORA 2024

作者： Al-Azzawi, Osamah Kurnaz, Sefer Department of Electrical & Computer Engineering Institute of Graduate Studies Altinbas University Istanbul Turkey

ISBN: (纸本)9798350394634

Through the use of the Gestational Diabetes Mellitus (GDM) Data Set, this research conducts an in-depth analysis of machine learning methods for the early diagnosis of GDM. The effectiveness of various algorithms is evaluated by the use of metrics such as recall, accuracy, precision, and F1 score. There are several algorithms that fall under this category, such as Logistic Regression, Long Short-Term Memory (LSTM), Gradient Boosting Classifier, Random Forest, and K-Nearest Neighbors. It is necessary to do meticulous data preparation in order to find the best models for GDM prediction. Some examples of this preparation include feature scaling and principal component analysis (PCA). Should this research prove to be effective, it has the potential to provide insight on how machine learning may be used to enhance the diagnosis and management of GDM. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Object Detection Enhancement Based on Super-Resolution Mapping 31

Object Detection Enhancement Based on Super-Resolution Mappi...

引用

31st International Conference on electrical engineering, ICEE 2023

作者： Abyazi, Danial Abyazi, Dadfar Yazdi, Mehran Institute for Advanced Studies in Basic Science University Department of Computer Engineering Zanjan Iran Shiraz University Department of Electrical and Computer Engineering Shiraz Iran School of Electrical and Computer Engineering Shiraz Uniersity Shiraz Iran

ISBN: (纸本)9798350312560

Object detection, while being a key step in many applications, has remained challenging, mainly due to the different resolutions of objects in an image. On the other hand, Super-Resolution (SR) approaches have recently been developed to improve the resolution of an image. In this paper, we utilize SR to enhance the quality of images before applying them to a detection model and propose a structure where the detection performance is improved. Furthermore, we remove the image noises by SR methods. Comparisons depict the superior visual performance of the proposed method compared to the conventional detection models. We evaluate our proposed method for detection of solar panels in two countries. To this aim, we created a dataset of satellite images needed for implementing detection models. As a result, we can simply evaluate the usage of solar panels in countries. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

GSKTM: efficient of query search for spatial keyword in text mining

引用

International Journal of Information and Communication Technology 2024年第4期25卷 352-379页

作者： Reddy, Ramya Rayacherlu Sambasadasiva Manu, Darshan Naveen Raju, G. Nimbhorkar, Sejal Santosh Rajuk, Venugopal Kuppanna Iyengar, S.S. Patnaik, L.M. Department of Computer Science and Engineering Dayananda Sagar College of Engineering Bangalore India Bangalore University Bengaluru India Department of Computer Science and Engineering Florida International University MiamiFL United States INSA National Institute of Advanced Studies Indian Institute of Science Campus Bangalore India

In today’s world, geo-positioning technologies, location-based services have attracted many researcher’s due to the increasing amount of spatio textual objects in various applications like social networks, geo location services. Each spatial object consists of spatial locations and a set of query terms. In this paper, an efficient group of query search for spatial keyword in text mining is proposed that retrieves both spatial and textual keyword objects to effectively reduce the search space. The clusters and subclusters are constructed based on the calculated range of the objects location and categories in the dataset. Further, categorylist is constructed that identifies the category of interest (CoI) of users query. Experiments are conducted on two real dataset namely Euro and geographic names. It is observed that GSKTM outperforms inverted linear quad-tree (ILQ) with improved response time and provides groupwise top-k results. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： group keyword query search spatial text feature selection

来源：评论

学校读者我要写书评

暂无评论

Advancements in Speech Recognition: Exploring Feature Extraction Techniques for Enhanced Accuracy and Human-Machine Communication 4

Advancements in Speech Recognition: Exploring Feature Extrac...

引用

4th International Conference on Advances in electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Bhavani, R. Kathirvelu, Kalaivani Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350343670

Speech Recognition (SR), for all diverse languages, is still a big challenge. SR is predominantly used in telecommunication, medical documentation, car control, aviation, etc. SR involves breaking down an audio signal of spoken words into discrete units and then matching those units to words in a language model. The main target of SR is to attain healthier verbal communication amid humans and machines. Therefore, it is a good technology of the human-machine crossing point. The SR uses the Feature Extraction (FE) techniques for better accuracy. In this paper, various techniques for FE are discussed, and an overview is provided to assist in selecting the most suitable technique for achieving higher accuracy. The review highlights the importance of developing more accurate and robust SR systems to improve the user experience in various domains. Overall, it provides the manuscript deals with five different techniques, and among them, the Mel-Frequency Cepstral Coefficients (MFCC) technique was found to exhibit a high level of accuracy. © 2024 IEEE.

关键词： feature extraction Signal processing Signals Sound Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A multi-modal approach for identifying schizophrenia using cross-modal attention 46

A multi-modal approach for identifying schizophrenia using c...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Premananth, Gowtham Siriwarden, Yashish M. Resnik, Philip Espy-Wilson, Carol University of Maryland Department of Electrical and Computer Engineering College ParkMD United States University of Maryland Institute for Advanced Computer Studies College ParkMD United States

ISBN: (纸本)9798350371499

This study focuses on how different modalities of human communication can be used to distinguish between healthy controls and subjects with schizophrenia who exhibit strong positive symptoms. We developed a multi-modal schizophrenia classification system using audio, video, and text. Facial action units and vocal tract variables were extracted as low-level features from video and audio respectively, which were then used to compute high-level coordination features that served as the inputs from the audio and video modalities. Context-independent text embeddings extracted from transcriptions of speech were used as the input for the text modality. The multi-modal system is developed by fusing a segment-to-session-level classifier for video and audio modalities with a text model based on a Hierarchical Attention Network (HAN), with cross-modal attention. The proposed multi-modal system outperforms the previous state-of-the-art multi-modal system by 8.53% in the weighted average F1 score. © 2024 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Multilingual Idioms and Similes in Large Language Models 31

Comparative Study of Multilingual Idioms and Similes in Larg...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Khoshtab, Paria Namazifard, Danial Masoudi, Mostafa Akhgary, Ali Sani, Samin Mahdizadeh Yaghoobzadeh, Yadollah School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Tehran Institute for Advanced Studies Khatam University Tehran Iran

ISBN: (纸本)9798891761964

This study addresses the gap in the literature concerning the comparative performance of LLMs in interpreting different types of figurative language across multiple languages. By evaluating LLMs using two multilingual datasets on simile and idiom interpretation, we explore the effectiveness of various prompt engineering strategies, including chain-of-thought, few-shot, and English translation prompts. We extend the language of these datasets to Persian as well by building two new evaluation sets. Our comprehensive assessment involves both closed-source (GPT-3.5, GPT-4o mini, Gemini 1.5), and open-source models (Llama 3.1, Qwen2), highlighting significant differences in performance across languages and figurative types. Our findings reveal that while prompt engineering methods are generally effective, their success varies by figurative type, language, and model. We also observe that open-source models struggle particularly with low-resource languages in similes. Additionally, idiom interpretation is nearing saturation for many languages, necessitating more challenging evaluations. © 2025 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

Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation 31

Extending LLMs to New Languages: A Case Study of Llama and P...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Sani, Samin Mahdizadeh Sadeghi, Pouya Vu, Thuy-Trang Yaghoobzadeh, Yadollah Haffari, Gholamreza Department of Electrical and Computer Engineering University of Tehran Iran Tehran Institute for Advanced Studies Khatam University Iran Department of Data Science & AI Monash University Australia

ISBN: (纸本)9798891761964

Large language models (LLMs) have made great progress in classification and text generation tasks. However, they are mainly trained on English data and often struggle with low-resource languages. In this study, we explore adding a new language, i.e., Persian, to Llama (a model with a limited understanding of Persian) using parameter-efficient fine-tuning. We employ a multi-stage approach involving pretraining on monolingual Persian data, aligning representations through bilingual pretraining and instruction datasets, and instruction-tuning with task-specific datasets. We evaluate the model's performance at each stage on generation and classification tasks. Our findings suggest that incorporating the Persian language, through bilingual data alignment, can enhance classification accuracy for Persian tasks, with no adverse impact and sometimes even improvements on English tasks. Additionally, the results highlight the model's initial strength as a critical factor when working with limited training data, with cross-lingual alignment offering minimal benefits for the low-resource language. Knowledge transfer from English to Persian has a marginal effect, primarily benefiting simple classification tasks. © 2025 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

Improved Deepmaxoutmodel for Disease Prediction in Healthcare IoT Cloud System 3

Improved Deepmaxoutmodel for Disease Prediction in Healthcar...

引用

3rd IEEE International Conference of Electron Devices Society Kolkata Chapter, EDKCON 2024

作者： Preetha, P. Packialatha, A. Vels Institute of Science Technology and Advanced Studies Department of Computer Science Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350374643

The Internet of Medical Things IoMT has grown rapidly due to the growing popularity of wearable technology and its applications in health monitoring systems. The IoMT significantly reduces the death rate by facilitating early sickness identification. Predicting cardiac disease is among the most significant issues with clinical dataset analysis. Finding the key components of heart disease prediction is the goal of the suggested investigation, which makes use of machine learning techniques. Despite several studies on the issue, the accuracy of the findings on the diagnosis of heart illness is low. The purpose of this paper is to provide an innovative framework for healthcare monitoring that includes the following phases. Data preprocessing, feature extraction, acquisition of data, and prediction are the primary stages. The process of acquiring data is at the IoTs layer. The medical data is considered in this case (benchmark datasets of different illnesses). The data pre-processing operations of data cleaning and data filtering at the cloud layer are applied to the data obtained from the IoT sensors (considering the dataset), where the data normalization process will take place. Subsequently, statistical features and raw features are extracted. The multi-layered Deepmaxout model will predict the diseases during in the prediction phase. Lastly, the evaluation of the suggested approach is compared to existing methods using several types of metrics. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Recognition of Deep Fake Voice Acoustic using Ensemble Bagging Model 5

Recognition of Deep Fake Voice Acoustic using Ensemble Baggi...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Basha, Shaik Abdul Yunus Priya, K.Ulaga Vels Institute of Science Technology & Advanced Studies Department of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350379945

As artificial speech generates technological evolution;fake voice information has become an increasingly prevalent avenue for fraud. Numerous investigations have been carried out into machine learning techniques, signal processing techniques, and the Automatic Speaker Verification System to address such issues. Since there are increasing methods to create fake information, techniques must be developed to determine when audio recordings employed as electronic proof are corrupted. Such recordings contain the potential to be manipulated. Hence, this research work identified the data regarding audio systems as either fake or real by i) extracting features from audio file metadata using oversampling techniques and ii) Developing an Ensemble Bagging Model appropriate for analyzing input audio signal followed by classification of fake (fraudulent) and real (authentic) audio. Our experimental results reveal that the ensemble bagging model attained an accuracy of 99.5%, precision of 99%, 99.6% recall, and 99.9% Fl-measure in the prediction of the audio system compared with traditional approaches. © 2024 IEEE.

关键词： Audio recordings

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：