检索结果-内蒙古大学图书馆

Enhancing English accent identification in automatic speech recognition using spectral features and hybrid CNN-BiLSTM model

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Ahmed, Ghayas Lawaye, Aadil Ahmad Jain, Vishal Chatterjee, Jyotir Moy Mahajan, Shubham Department of Computer Sciences Baba Ghulam Shah Badshah University J&K Rajouri India Department of Computer Science & Engineering Sharda University Noida India Dehradun India Department of Computer Science & Engineering Amity University Haryana India

Automatic Speech Recognition (ASR) has been the regnant research area in the domain of Natural Language Processing for the last few decades. Past years’ advancement provides progress in this area of research. The accent of spoken is the prominent factor affecting the performance of ASR. Accent is the pronunciation of a word in a distinct way which may vary from specimen to specimen depending upon their social class, formality, age, vocal property, gender, geography, and influence of native or other language. Recognizing an accent requires various complex characteristics and features of voice such as voice quality, prosody, and phoneme pronunciation which are difficult to extract and analyze. To solve these difficulties, the researchers focus their attention on spectral representation such as Mel Spectrogram and Mel-Frequency Cepstral Coefficient (MFCC). In this study, we will analyze which features achieve maximum accuracy for the English accent classification task. Here in this work, we perform our experiments on Log Mel filter bank and MFCC features with four different window function. We extract features from raw audio with various windowing function and train a hybrid model of Convolutional Neural Network and Bidirectional Long Short-term Memory network (CNN-BiLSTM) on a custom dataset having nine different accents of English language namely American, Australian, British, Indian (Oriya, Bangla, Telegu, Malayalam), and Welsh. The accuracy of each feature is evaluated and compared. The log Mel filter bank outputs the highest accuracy of 99.75% and 99.91% of training and validation with Han window function while MFCC with Bartlett window function achieves 99.98% of training and 99.33% of validation accuracy. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Sign language detection using convolutional neural network

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第4期15卷 2399-2424页

作者： Rakshit, Pranati Paul, Sarbajeet Dey, Shruti Computer Science & amp Engineering Department JIS College of Engineering West Bengal Kalyani India

Sign language recognition is an important social issue to be addressed which can benefit the deaf and hard of hearing community by providing easier and faster communication. Some previous studies on sign language recognition have used complex input modalities and feature extraction methods, limiting their practical applicability. This research aims to compare two custom-made convolutional neural network (CNN) models for recognizing American Sign Language (ASL) letters from A to Z, and determine which model performs better. The proposed models utilize a combination of CNN and Softmax activation function, which are powerful and widely used classification methods in the field of computer vision. The purpose of the proposed study is to compare the performance of two specially created CNN models for identifying 26 distinct hand signals that represent the 26 English alphabets. The study found that Model_2 had better overall performance than Model_1, with an accuracy of 98.44% and F1 score 98.41%. However, the performance of each model varied depending on the specific label, suggesting that the choice of model may depend on the specific use case and the labels of interest. This research contributes to the growing field of sign language recognition using deep learning techniques and highlights the importance of designing custom models. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient video summarization through MobileNetSSD: a robust deep learning-based framework for efficient video summarization focused on objects of interest

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Yarrarapu, Manasa Leelavathy, Narkedamilly Haritha, Dasari Department of Computer Science and Engineering Jawaharlal Nehru Technological University Andhra Pradesh Kakinada533003 India Department of Computer Science and Engineering Godavari Institute of Engineering and Technology Andhra Pradesh Rajahmundry533296 India Department of Computer Science and Engineering University College of Engineering Jawaharlal Nehru Technological University Andhra Pradesh Kakinada533003 India

Now-a-days, the generation of videos has increased dramatically due to the quick growth of multimedia and the internet. The need for effective ways to store, manage, and index the massive numbers of videos has become imperative due to this expansion. As a result, a method needs to be proposed that collects only the necessary data from the original recording. In computer vision, Video summarization is a significant task, and its primary goal is to give a quick summary of the video by removing irrelevant information and capturing key frames from the video. Many approaches have developed over the last several decades, using the most recent deep neural network architectures that represent the current state-of-the-art. Our method involves extracting vital key frames from the input video using the MobileNetSSD model, which is well-known for its efficient recognition and localization of objects of interest. These highlighted frames are essential in creating a detailed video summary. Furthermore, a method of temporal analysis is applied to guarantee that the summary accurately reflects the relevant events in the order in which they occurred, contributing to a coherent and meaningful representation of the information. We evaluated the proposed approach on TV Sum and SUM me video datasets, comparing the results against cutting-edge video summarization techniques. Our approach works effectively to produce clear and meaningful video summaries. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Ransomware on cyber-physical systems: Taxonomies, case studies, security gaps, and open challenges

引用

Internet of Things and Cyber-Physical Systems 2024年第1期4卷 186-202页

作者： Benmalek, Mourad Computer Engineering Department College of Engineering and Architecture Al Yamamah University Riyadh Saudi Arabia

Ransomware attacks have emerged as one of the most significant cyberthreats faced by organizations worldwide. In recent years, ransomware has also started to target critical infrastructure and Cyber-Physical Systems (CPS) such as industrial control systems, smart grids, and healthcare networks. The unique attack surface and safety-critical nature of CPS introduce new challenges in defending against ransomware. This paper provides a comprehensive overview of ransomware threats to CPS. We propose a dual taxonomy to classify ransomware attacks on CPS based on infection vectors, targets, objectives, and technical attributes. Through an analysis of 10 real-world incidents, we highlight attack patterns, vulnerabilities, and impacts of ransomware campaigns against critical systems and facilities. Based on the insights gained, we identify open research problems and future directions to improve ransomware resilience in CPS environments. © 2024 The Author

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Modeling of Optimal Deep Learning Based Flood Forecasting Model Using Twitter Data

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 1455-1470页

作者： G.Indra N.Duraipandian Department of Computer Science and Engineering RMK College of Engineering and TechnologyChennai601206India Department of Computer Science and Engineering Saveetha Engineering CollegeChennai602106India

Aﬂood is a signiﬁcant damaging natural calamity that causes loss of life and *** work on the construction ofﬂood prediction models intended to reduce risks,suggest policies,reduce mortality,and limit property damage caused byﬂ*** massive amount of data generated by social media platforms such as Twitter opens the door toﬂood *** of the real-time nature of Twitter data,some government agencies and authorities have used it to track natural catastrophe events in order to build a more rapid rescue ***,due to the shorter duration of Tweets,it is difﬁcult to construct a perfect prediction model for determiningﬂ*** learning(ML)and deep learning(DL)approaches can be used to statistically developﬂood prediction *** the same time,the vast amount of Tweets necessitates the use of a big data analytics(BDA)tool forﬂood *** this regard,this work provides an optimal deep learning-basedﬂood forecasting model with big data analytics(ODLFF-BDA)based on Twitter *** suggested ODLFF-BDA technique intends to anticipate the existence ofﬂoods using tweets in a big data *** ODLFF-BDA technique comprises data pre-processing to convert the input tweets into a usable *** addition,a Bidirectional Encoder Representations from Transformers(BERT)model is used to generate emotive contextual embed-ding from ***,a gated recurrent unit(GRU)with a Multilayer Convolutional Neural Network(MLCNN)is used to extract local data and predict theﬂ***,an Equilibrium Optimizer(EO)is used toﬁne-tune the hyper-parameters of the GRU and MLCNN models in order to increase prediction *** memory usage is pull down lesser than 3.5 MB,if its compared with the other algorithm *** ODLFF-BDA technique’s performance was validated using a benchmark Kaggle dataset,and theﬁndings showed that it outperformed other recent approaches signiﬁcantly.

关键词： Big data analytics predictive models deep learning ﬂood prediction twitter data hyperparameter tuning

来源：评论

学校读者我要写书评

暂无评论

Unraveling the intricacies of EEG seizure detection: A comprehensive exploration of machine learning model performance, interpretability, and clinical insights

引用

Multimedia Tools and Applications 2024年第41期83卷 89217-89247页

作者： Mridha, Krishna Priyok, Masrur Ahsan Shukla, Madhu Department of Computer Engineering Marwadi University Rajkot India Department of Software Engineering Tianjin University Tianjin China Department of Computer Engineering Artificial Intelligence and Big Data Analytics Marwadi University Gujarat Rajkot India

In neurology, it is critical to promptly and precisely identify epileptic episodes using EEG data. Interpretability and thorough model evaluation are still crucial to guarantee reliability, even though machine learning provides sophisticated tools for automated EEG analysis. We undertook a thorough investigation of EEG seizure classification in this work, with equal emphasis on statistical validation, interpretability, and model performance. Following thorough preprocessing, we used statistical significance tests in conjunction with Chernoff and Bhattacharyya Bounds to select features. Top performers were found to be the Random Forest which had accuracies of 96%. A paired t-test and bootstrapped 95% confidence intervals were used to statistically validate the performance robustness, demonstrating the large variation in model performances. Going beyond simple performance measures, we set out to decipher the nuances of model choices by utilizing methods devoted to model interpretability and shedding light on the importance of distinct aspects. This helped neurologists grasp the primary EEG indicators predictive of seizures and opened the door for future clinical insights. It also provided transparency in diagnostic predictions. Our efforts highlight the mutually reinforcing importance of predictability and model interpretability in the context of medical machine-learning applications, hence intensifying the demand for the creation and use of trustworthy and transparent neurology diagnostic instruments. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Neurology

来源：评论

学校读者我要写书评

暂无评论

Secure Data Communication in a Clustered Network in Wireless Sensor Networks using AES Cipher 15

Secure Data Communication in a Clustered Network in Wireless...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Manjunatha, A.S. Venkatramana Bhat, P. Department of Computer and Communication Engineering India Department of Computer Science and Engineering India

ISBN: (纸本)9798331300579

Data is collected and forwarded to the cluster head by sensor nodes in the Wireless Sensor Network (WSN). Ensuring the confidentiality and integrity of the data that must be provided to the base station is tough. We recommend using a simple Caesar cipher and Advanced Encryption Standard (AES) technique at the cluster head node level for effective communication from the cluster head to the base station with little power consumption. © Grenze Scientific Society, 2024.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Hybrid Underwater Target Tracking with Particle Filters and Deep Learning;Focus on Design Considerations 8

Hybrid Underwater Target Tracking with Particle Filters and ...

引用

8th International Symposium on Innovative Approaches in Smart Technologies, ISAS 2024

作者： Baba, Abdullatif Alothman, Basil Computer Science and Engineering Department Kuwait Computer Engineering Department Ankara Turkey

ISBN: (纸本)9798331540104

This paper explores essential aspects of autonomous underwater vehicle (AUV) design, focusing on hull structure, hydrodynamics, propulsion systems, and sensor integration. It also examines the role of underwater Simultaneous Localization and Mapping (SLAM) in improving navigation and mapping precision for AUVs. In addition, the paper addresses challenges and solutions related to underwater GPS systems. The primary contribution of this study is a novel tracking method that combines the Particle Filter (PF) with deep learning techniques to enhance the tracking capabilities of underwater maneuvering targets. Multiple simulations validate the effectiveness of the proposed approach in diverse trajectory scenarios. © 2024 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Received Power Based Unmanned Aerial Vehicles (UAVs) Jamming Detection and Nodes Classification Using Machine Learning

引用

computers, Materials & Continua 2023年第4期75卷 1253-1269页

作者： Waleed Aldosari Department of Computer Engineering College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia

This paper presents a machine-learning method for detecting jamming UAVs and classifying nodes during jamming attacks onWireless Sensor Networks(WSNs).Jamming is a type of Denial of Service(DoS)attack and intentional interference where a malicious node transmits a high-power signal to increase noise on the receiver side to disrupt the communication channel and reduce performance *** defend and prevent such attacks,the first step is to detect *** current detection approaches use centralized techniques to detect jamming,where each node collects information and forwards it to the base *** a result,overhead and communication costs *** this work,we present a jamming attack and classify nodes into different categories based on their location to the jammer by employing a single node *** a result,we introduced a machine learning model that uses distance ratios and power received as features to detect such ***,we considered several types of jammers transmitting at different power levels to evaluate the proposed metrics using *** a detection accuracy of 99.7%for the k-nearest neighbors(KNN)algorithm and average testing accuracy of 99.9%,the presented solution is capable of efficiently and accurately detecting jamming attacks in wireless sensor networks.

关键词： Jamming attacks machine learning unmanned aerial vehicle(UAV) WSNs

来源：评论

学校读者我要写书评

暂无评论

Efficient Deployment Using CI/CD: Text Summarization Using NLP in Cloud 1

Efficient Deployment Using CI/CD: Text Summarization Using N...

引用

1st International Conference on AIML-Applications for engineering and Technology, ICAET 2025

作者： Shingade, Bhuvan Hariharan, Siddharth Patole, Amol Singh, Kishan TPCT's Terna Engineering College Department of Computer Engineering Mumbai India Watumull Institute of Electronics Engineering and Computer Technology Department of Computer Engineering Mumbai India

ISBN: (纸本)9798350355611

The core task in natural language processing (NLP) is text summarization, which condenses important information from large volumes of text into brief summaries. This study reviews text summarization strategies using NLP principles, focusing on two main methods: extractive and abstractive summarization. Abstractive techniques generate summaries by interpreting and rephrasing information, while extractive methods highlight key sentences or paragraphs from the original text. Our study examines various algorithms and models within both paradigms, leading to the development of a novel summarization model. Inspired by advancements in deep learning and transformer architectures, our model integrates state-of-the-art techniques to produce high-quality summaries. We discuss the architecture, training, and evaluation of our model, demonstrating its effectiveness on benchmark datasets. Lastly, we explore potential applications and future directions, emphasizing the importance of custom-built solutions for modern information processing tasks. © 2025 IEEE.

关键词： Inverse problems

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：