检索结果-内蒙古大学图书馆

Automatic emotion recognition using deep neural network

Multimedia Tools and Applications 2025年 1-30页

作者： Sujatha, R. Chatterjee, Jyotir Moy Pathy, Baibhav Hu, Yu-Chen School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India Department of CSE Graphic Era University Dehradun India School of Electrical Engineering Vellore Institute of Technology Vellore India Department of Computer Science Tunghai University Taichung City Taiwan

Emotions are a vital semantic part of human correspondence. Emotions are significant for human correspondence as well as basic for human–computer cooperation. Viable correspondence between people is possibly achieved when both the importance and the emotion of the correspondence are perceived by all groups included. Understanding the significance of language has generally been concentrated on in natural language processing (NLP) as a semantic examination. In NLP, the text can be handled appropriately for classification. Emotion detection from facial emotion is the subfield of social signal processing applied in a wide assortment of regions, explicitly for human and PC collaboration. Many researchers have proposed various approaches, generally utilizing machine learning concepts. Automatic emotion recognition (AER) is significant for working with consistent intuitiveness between a person and a smart device toward fully acknowledging an intelligent society. Many researchers examined cross-lingual and multilingual speech emotion as a stage toward language-free emotion acknowledgment in natural speech. In the present work, we are proposing a deep learning-based AER system using four openly accessible datasets, namely Basic Arabic Vocal Emotions Dataset (BAVED), Acted Emotional Speech Dynamic Database (AESDD), Urdu written in Latin/Roman Script (URDU), and Toronto Emotional Speech Set (TESS), by utilizing the Jupyter notebook and a Python library for music and audio synthesis named Librosa. The experimental results exhibited that the proposed approach achieves better than the existing approaches, i.e., the accuracy of the proposed system with the URDU dataset is 96.24%, the TESS dataset is 99.10%, the AESDD dataset is 65.97%, and the BAVED dataset is 73.12%. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Optimized deep learning-oriented strategy for predicting the location of delamination and detecting their shapes in composite structures

引用

Iran Journal of computer science 2025年 1-16页

作者： Demircioğlu, Ufuk Bakır, Halit Mechanical Engineering Department Sivas University of Science and Technology Sivas Türkiye Computer Engineering Department Sivas University of Science and Technology Sivas Türkiye

In this paper, the possibilities of deep learning approaches for sandwich structure delamination detection and prediction have been investigated. The research was divided into three parts: a validation study, a classification analysis of delamination shape, and delamination location forecasting. The best mesh configuration in terms of computational time and accuracy was chosen during the validation study by comparing a COMSOL MULTIPHYSICS model’s results with those obtained in a previously conducted related study. The natural frequencies of sandwich beams with various delamination forms and locations were collected from COMSOL MULTIPHYSICS and used in the classification and regression studies. Deep learning (DL) models were trained to predict the location of delamination and detect the shape of delamination using the obtained dataset. To improve accuracy and generalizability, we proposed tuning the hyperparameters of the model to choose the best DL structures for achieving both regression and shape detection tasks with as high performance as possible. The Bayesian algorithm was used to select the best combination of values for multiple hyperparameters used in the regression and classification models. Furthermore, several optimization phases have been held to explore the hyperparameter space carefully. In the optimization study, various regression and classification metrics were used to determine the optimum model. The outcomes demonstrate that both delamination location prediction and shape detection were accomplished with excellent performance by the optimized deep learning models. Particularly, a mean squared error value of 0.0000043303 was achieved, which allows regression analysis to identify the location of the delamination accurately. Likewise, 0.9944 of accuracy value has been achieved for the shape detection analysis, which allows the model to identify delamination shapes precisely. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2

关键词： Deep learning Finite element method Hyperparameter tuning Sandwich structures delamination

来源：评论

学校读者我要写书评

暂无评论

Features enhancement of micro-service based cab booking system using block-chain 4th

Features enhancement of micro-service based cab booking syst...

引用

4th International Conference on Computational Methods in science and technology, ICCMST 2024

作者： Rohit Singh, Neelaksh Shukla, Riya Singh, Ashutosh Kumar Department of Computer Science and Engineering Institute of Engineering and Rural Technology Prayagraj India Department of Computer Science and Engineering United College of Engineering and Research Prayagraj India

ISBN: (纸本)9781032911571

Cab booking services help people order taxis. Existing cab booking services use client server-based architecture. The paper gives a study of the architecture and workings of the Uber cab booking website (Dissanayake, March 18, 2021). It has a micro-service based architecture (Li et al. 2021). Load balancing (Al-Jaroodi et al. 2012) and stream processing (Besnard et al. 2013) are used to handle a large number of requests. The workload is divided among servers using Dispatch Optimization (Abid et al. 2022). It ensures fast responses, easy connection minimal downtime, and efficient use of resources. However, the use of servers increases the cost of service. Rider and driver depend on the server to connect. They don’t know if the system is charging them fairly. It reduces transparency and trust. The paper proposes a blockchain-based cab booking application to solve some of the problems. Trust, transparency, and decentralization can be ensured using blockchain. Transparent and immutable ledgers of blockchain ensure trust and reduce reliance on intermediaries. Smart contracts govern ride management, optimizing efficiency. Blockchain capabilities are used to ensure fair rides, direct interaction of passengers with drivers, and automated payments. The proposed system aims at combining existing technology with blockchain solution to ensure security and transparency along with scalability and quick response time. © 2025 the Author(s).

关键词： Reservation systems

来源：评论

学校读者我要写书评

暂无评论

BNSENTMIX: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis 1

BNSENTMIX: A Diverse Bengali-English Code-Mixed Dataset for ...

引用

1st Workshop on Language Models for Low-Resource Languages, LoResLM 2025 - co-located at the 31st International Conference on Computational Linguistics, COLING 2025

作者： Alam, Sadia Farhan Ishmam, Md. Alvee, Navid Hasin Shahnewaz Siddique, Md. Kamal, Abu Raihan Mostofa Azam Hossain, Md. Department of Computer Science and Engineering Islamic University of Technology Bangladesh

ISBN: (纸本)9798891762152

The widespread availability of code-mixed data in digital spaces can provide valuable insights into low-resource languages like Bengali, which have limited annotated corpora. Sentiment analysis, a pivotal text classification task, has been explored across multiple languages, yet code-mixed Bengali remains underrepresented with no large-scale, diverse benchmark. Code-mixed text is particularly challenging as it requires the understanding of multiple languages and their interaction in the same text. We address this limitation by introducing BNSENTMIX, a sentiment analysis dataset on code-mixed Bengali comprising 20,000 samples with 4 sentiment labels, sourced from Facebook, YouTube, and e-commerce sites. By aggregating multiple sources, we ensure linguistic diversity reflecting realistic code-mixed scenarios. We implement a novel automated text filtering pipeline using fine-tuned language models to detect code-mixed samples and expand code-mixed text corpora. We further propose baselines using machine learning, neural networks, and transformer-based language models. The availability of a diverse dataset is a critical step towards democratizing NLP and ultimately contributing to a better understanding of code-mixed languages. © 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

Blockchain-based knowledge-aware semantic communications for remote driving image transmission

引用

Digital Communications and Networks 2025年第2期11卷 317-325页

作者： Yangfei Lin Tutomu Murase Yusheng Ji Wugedele Bao Lei Zhong Jie Li Department of Computer and Network Engineering University of Electro-Communications Information Technology Center Nagoya University National Institute of Informatics(NII) Hohhot Minzu College Toyota Motor Corporation Department of Computer Science and Engineering Shanghai Jiaotong University

Remote driving, an emergent technology enabling remote operations of vehicles, presents a significant challenge in transmitting large volumes of image data to a central server. This requirement outpaces the capacity of traditional communication methods. To tackle this, we propose a novel framework using semantic communications, through a region of interest semantic segmentation method, to reduce the communication costs by transmitting meaningful semantic information rather than bit-wise data. To solve the knowledge base inconsistencies inherent in semantic communications, we introduce a blockchain-based edge-assisted system for managing diverse and geographically varied semantic segmentation knowledge bases. This system not only ensures the security of data through the tamper-resistant nature of blockchain but also leverages edge computing for efficient management. Additionally, the implementation of blockchain sharding handles differentiated knowledge bases for various tasks, thus boosting overall blockchain efficiency. Experimental results show a great reduction in latency by sharding and an increase in model accuracy, confirming our framework's effectiveness.

关键词： Semantic communication Remote driving Semantic segmentation Blockchain Knowledge base management

来源：评论

学校读者我要写书评

暂无评论

Comprehensive insights into healthcare IoT: the role of machine learning and deep learning approaches

引用

Multimedia Tools and Applications 2025年 1-42页

作者： Kumar, Atul Dewang, Rupesh Kumar Computer Science and Engineering Department Motilal Nehru National Institute of Technology Allahabad Uttar Pradesh Prayagraj211004 India

Conventional healthcare systems have long struggled to address the varied needs of large patient populations, often leading to inefficiencies and less-than-optimal outcomes. Yet, the advent of machine learning (ML) and deep learning (DL) models has heralded a transformative shift toward value-based care, enabling healthcare providers to offer personalized and remarkably effective treatments. Contemporary medical equipment and devices are equipped with internal applications that gather and store extensive patient data, forming a valuable resource for ML-powered predictive *** have conducted a systematic literature review (SLR) which mainly focuses on Theoretical background, challenges, Application framework, Organization of IoT in healthcare and HIoT *** the SLR process some efficient methodologies has been used. In the SLR process we have conducted Quality metadata analysis (QMA) which provides the complete statistical analysis by considering different *** learning algorithms enable the analysis of the extensive data produced by IoT devices, uncovering patterns and irregularities that may escape human detection. Deep learning, leveraging sophisticated neural network models, enhances the accuracy of medical image interpretation, disease prognosis, and forecasting patient outcomes. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Design of a Multifactor Unidentified Remote End User Authentication Mechanism for IoT Network

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第10期49卷 191-204页

作者： Sharma, Neha Dhiman, Pankaj Department of Computer Science and Engineering Jaypee University of Information Technology Waknaghat H. P. Solan India

The rapid proliferation of Internet of Things (IoT) devices, coupled with the rollout of advanced 5G networks, has generated significant concerns regarding security breaches. These concerns stem from the expanded attack surfaces that come with improved connectivity, making IoT systems more vulnerable to malicious threats. A crucial strategy to counter these security challenges is the implementation of robust user authentication methods. Despite numerous proposals for multi-factor authentication mechanisms, many of these systems exhibit weaknesses, particularly in their susceptibility to user impersonation attacks and the risks posed by stolen mobile devices. Furthermore, several schemes fail to incorporate essential features such as session key agreements or backup solutions for instances of lost or stolen devices and compromised private keys. To address urgent security challenges in IoT environments, we developed a three-factor user authentication system tailored for low-cost IoT devices. This system tackles critical vulnerabilities while maintaining low computing and communication costs, enhancing security without compromising usability and efficiency. © 2025 Slovene Society Informatika. All rights reserved.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Visual Robustness Benchmark for Visual Question Answering (VQA)

Visual Robustness Benchmark for Visual Question Answering (V...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Ishmam, Md Farhan Tashdeed, Ishmam Saadat, Talukder Asir Ashmafee, Md Hamjajul Mostofa Kamal, Abu Raihan Hossain, Md. Azam Islamic University of Technology Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798331510831

Can Visual Question Answering (VQA) systems maintain their performance when deployed in the real world? Or are they susceptible to realistic corruption effects, e.g., image blur, which can be detrimental in sensitive applications such as medical VQA? While linguistic robustness has been thoroughly explored within the VQA literature, there has yet to be any significant work on visual robustness. In this work, we present the first large-scale benchmark to evaluate the visual robustness of VQA models, including multimodal large language models and zero-shot evaluation, and assess the strength of the realistic corruption effects. Additionally, we have designed several robustness evaluation metrics that quantify an aspect of robustness. These sub-metrics can be aggregated into a unified metric and tailored to fit a variety of use cases. The experiments reveal important insights into the relationships between model size, accuracy, and robustness against the visual corruptions. Our benchmark highlights the need for a balanced approach in model development that considers model performance without compromising robustness. © 2025 IEEE.

关键词： common corruptions corruption robustness evaluation metric multimodal multimodal benchmark multimodal evaluation multimodal learning multimodal robustness robustness robustness benchmark robustness evaluation robustness metric vision language vision language evaluation vision language metric vision language robustness visual corruption visual question answering visual robustness vqa vqa benchmark vqa evaluation vqa metric vqa robustness

来源：评论

学校读者我要写书评

暂无评论

Dual image based secured reversible data hiding scheme exploiting huffman compression tree combining bit-reversal permutation technique

引用

Multimedia Tools and Applications 2025年第9期84卷 5653-5698页

作者： Datta, Kankana Jana, Biswapati Chakraborty, Mamata Dalui Department of Computer Applications Haldia Institute of Technology HIT Campus Hatiberia Haldia Purba Medinipur West Bengal Haldia India Department of Computer Science Vidyasagar University West Bengal Midnapore India Department of Computer Science and Engineering National Institute of Technology West Bengal Durgapur India

In the area of data hiding and information security, the greater need is to ensure high embedding capacity of the stego media without hampering the visual quality while ensuring the tightest possible security. Now, it has become one of the biggest challenge to meet all these requirements. Embedding secret messages in dual images is one of the latest techniques that aims to cater such needs. However, there are very few data hiding schemes that are currently using dual images, but are suffering from several shortcomings, such as security loophole and poor visual quality with limited hiding capacity. In this paper, a dual image-based reversible data hiding scheme has been proposed where multiple bits can be embedded within a pair of pixels dynamically by Huffman compression where different pseudo codes are generated for different chunk of secret bits which are embedded by Bit-Reversal Permutation (BRP) and X-OR operations. Finally, pixels are interchanged between the dual images based on odd-even properties of the pixel values. The functional efficiency of the proposed scheme is evaluated by comparing the relevant parameters of different state-of-the-art schemes. It is established that the proposed scheme provides more than 64 dB PSNR value on average after embedding a maximum of 3, 27, 680 bits of secret data which ensures good visual quality and high embedding capacity as compared to other state-of-the-art schemes thereby benefitting innumerable applications across public and private sectors. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Enhancing Crop Health Monitoring: A ResNet50 Approach to Automated Plant Disease Severity Prediction

Enhancing Crop Health Monitoring: A ResNet50 Approach to Aut...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Gunavathi, H.S. Priya, Ishani Sree, Kothakota Bindhu Kushwaha, Aparna Bangalore Institute of Technology Department of Computer Science & Engineering India

ISBN: (纸本)9798331529833

Plant diseases significantly impact agricultural productivity, making it essential to accurately assess not only the presence of disease but also its severity. This paper presents a deep learning-based framework using ResNet50 to predict plant disease severity across multiple levels (Healthy, Mild, Moderate, and Severe). The system is designed to process plant leaf images, perform augmentation to improve robustness and classify disease severity with high accuracy. The proposed method leverages labelled and pseudo- labelled datasets to enhance the model's performance through data augmentation and training on unlabelled images. The results demonstrate the model's effectiveness in distinguishing between varying levels of disease progression, providing valuable insights for early intervention and optimized crop management strategies. This platform is crucial for automating plant disease severity monitoring, and aiding decision-making processes for timely interventions in agriculture. © 2025 IEEE.

关键词： agriculture data augmentation deep learning image classification plant disease ResNet50 severity prediction

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：