检索结果-内蒙古大学图书馆

Automatic speaker identification system based on MLP network and deep learning in the presence of severe interference

引用

Multimedia Tools and Applications 2025年 1-42页

作者： Shafik, Amira Sedik, Ahmed El-Shafai, Walid Khalaf, Ashraf A. M. El-Rabaie, El-Sayed M. El-Samie, Fathi E. Abd Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Electrical Engineering Faculty of Engineering Minia University Minia61519 Egypt Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafr Elsheikh University Kafr El‑Shaikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Automatic Speaker Identification (ASI) is so crucial for security. Current ASI systems perform well in quiet and clean surroundings. However, in noisy situations, the robustness of an ASI system against additive noise and interference is a crucial factor. An investigation of the impact of interference on ASI system performance is presented in this paper, which introduces algorithms for achieving high ASI system performance. The objective is to resist the interference of various forms. This paper presents two models for the ASI task in the presence of interference. The first one depends on Normalized Pitch Frequency (NPF) and Mel-Frequency Cepstral Coefficients (MFCCs) as extracted features and Multi-Layer Perceptron (MLP) as a classifier. In this model, we investigate the utilization of a Discrete Transform (DT), such as Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Discrete Sine Transform (DST), to increase the robustness of extracted features against different types of degradation through exploiting the sub-band decomposition characteristics of DWT and the energy compaction property of DCT and DST. This is achieved by extracting features directly from contaminated speech signals in addition to features extracted from discrete transformed signals to create hybrid feature vectors. The enhancement techniques, such as Spectral Subtraction (SS), Winer Filter, and adaptive Wiener filter, are used in a preprocessing stage to eliminate the effect of the interference on the ASI system. In the second model, we investigate the utilization of Deep Learning (DL) based on a Convolutional Neural Network (CNN) with speech signal spectrograms and their Radon transforms to increase the robustness of the ASI system against interference effects. One of this paper goals is to introduce a comparison between the two models and build a more robust ASI system against severe interference. The experimental results indicate that the two proposed models lead to satisfa

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

Multi-View Test-Time Adaptation for Semantic Segmentation in Clinical Cataract Surgery

引用

IEEE Transactions on Medical Imaging 2025年第5期44卷 2307-2318页

作者： Li, Heng Ou, Mingyang Li, Haojin Qiu, Zhongxi Niu, Ke Fu, Huazhu Liu, Jiang Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems Shenzhen518055 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China Beijing Information Science and Technology University Computer School Beijing100192 China Institute of High Performance Computing Agency for Science Technology and Research Fusionopolis Way 138632 Singapore Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Shenzhen518055 China

Cataract surgery, a widely performed operation worldwide, is incorporating semantic segmentation to advance computer-assisted intervention. However, the tissue appearance and illumination in cataract surgery often differ among clinical centers, intensifying the issue of domain shifts. While domain adaptation offers remedies to the shifts, the necessity for data centralization raises additional privacy concerns. To overcome these challenges, we propose a Multi-view Test-time Adaptation algorithm (MUTA) to segment cataract surgical scenes, which leverages multi-view learning to enhance model training within the source domain and model adaptation within the target domain. In the training phase, the segmentation model is equipped with multi-view decoders to boost its robustness against variations in cataract surgery. During the inference phase, test-time adaptation is implemented using multi-view knowledge distillation, enabling model updates in clinics without data centralization or privacy concerns. We conducted experiments in a simulated cross-center scenario using several cataract surgery datasets to evaluate the effectiveness of MUTA. Through comparisons and investigations, we have validated that MUTA effectively learns a robust source model and adapts the model to target data during the practical inference phase. © 1982-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Price Prediction Using Deep Learning Models 4

Bitcoin Price Prediction Using Deep Learning Models

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Hajare, Rasika Puri, Chetan Gote, Pradnyawant M. Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

Forecasting the price of bitcoins is significant in contemporary research, given the fact that the digital currency is relatively unpredictable and highly integrated in global securities markets. This paper compares the use of three deep learning models, namely recurrent neural networks (RNN), gated recurrent unit (GRU), and a convolutional neural network-long short-term memory (CNN-LSTM) for Bitcoin price prediction. Historical Bitcoin price data is used in the dataset, and every one of the models is trained and tested based on its performance to predict future prices based on past data. The proposed models include the RNN and GRU, which incorporate sequential dependency mappings to learn complex sequences, and the CNN-LSTM structures combine convolution layers for feature extraction and LSTM layers for sequencing. Different models' competency is discussed using the averaged Mean Squared Error (MSE) and graphs of the model's prediction against actual prices. The experimental results reveal that the proposed CNN-LSTM model has better prediction accuracy than RNN and GRU in time-series forecasting tasks, indicating that more complex architecture hybrid models might provide better forecasting performance. In analyzing and analyzing cryptocurrency price dynamics, this investigation gives information about the opportunities and challenges of these models to enhance future research. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Secure Channel Estimation Using Norm Estimation Model for 5G Next Generation Wireless Networks

引用

computers, Materials & Continua 2025年第1期82卷 1151-1169页

作者： Khalil Ullah Song Jian Muhammad Naeem Ul Hassan Suliman Khan Mohammad Babar Arshad Ahmad Shafiq Ahmad Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650500China Department of Computer Science Abbottabad University of Science and TechnologyHavelianAbbottabad22500Pakistan Department of Computing and Electronics Engineering Middle East CollegeMuscat124Oman Department of CS&IT Pak-Austria Fachhochschule Institute of Applied Sciences and Technology MangHaripur22621Pakistan Industrial Engineering Department College of EngineeringKing Saud UniversityRiyadh11421Saudi Arabia

The emergence of next generation networks(NextG),including 5G and beyond,is reshaping the technological landscape of cellular and mobile *** networks are sufficiently scaled to interconnect billions of users and *** in academia and industry are focusing on technological advancements to achieve highspeed transmission,cell planning,and latency reduction to facilitate emerging applications such as virtual reality,the metaverse,smart cities,smart health,and autonomous *** continuously improves its network functionality to support these *** input multiple output(MIMO)technology offers spectral efficiency,dependability,and overall performance in *** article proposes a secure channel estimation technique in MIMO topology using a norm-estimation model to provide comprehensive insights into protecting NextG network components against adversarial *** technique aims to create long-lasting and secure NextG networks using this extended *** viability of MIMO applications and modern AI-driven methodologies to combat cybersecurity threats are explored in this ***,the proposed model demonstrates high performance in terms of reliability and accuracy,with a 20%reduction in the MalOut-RealOut-Diff metric compared to existing state-of-the-art techniques.

关键词： Next generation networks massive mimo communication network artificial intelligence 5G adversarial attacks channel estimation information security

来源：评论

学校读者我要写书评

暂无评论

The Impact of TV White Space (TVWS) and 5G Networks on Bimodal Learning for Master's Programs in engineering science at the Higher Institute of Technology, University of Bangui

The Impact of TV White Space (TVWS) and 5G Networks on Bimod...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Ndassimba, Edgard Zoh-Ponguele, Nathan Kossingou, Ghislain Mervyl Saint-Juste Faculty of Science University of Bangui Department of Computer Engineering Bangui Central African Republic

ISBN: (数字)9798331512965

ISBN: (纸本)9798331512965

In this study, we presente digital solution for training master's students in engineering sciences, using a bimodal learning approach at the Higher Institute of Technology of Bangui's University. This proposal addresses the lack of master's-level programs in DevOps and Network Telecommunications, as well as the insufficient expertise of local educators in Information and Communication Technology (ICT). It also aims to strengthen the instruction of science, technology, engineering, and mathematics (STEM). The solution is based on remote learning platforms hosted in the public cloud, engaging students and teachers in a bimodal teaching model that delivers simultaneous instruction to both inperson and remote students via a high-speed TV White Space (TVWS) and 5G network. The expected impact is the training of competent engineers capable of successfully carrying out projects in the domain of information and communication technology, thereby contributing to the development of the Central African Republic. © 2025 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Empirical techniques for effort estimation in designing effective ML models

引用

International Journal of computers and Applications 2025年第2期47卷 226-234页

作者： Padmanabha Reddy, Y.C.A. Kosuru, Sai Sathwik Sirisalla, Nageswara Rao Vivekananda, G.N. Perala, Venkata Akanksha Department of Artificial Intelligence and Machine Learning Chaitanya Bharati Institute of Technology Telangana Hyderabad India Department of CSE B V Raju Institute of Technology Telangana Narsapur India Department of Computer Science and Engineering K.S.R.M. College of Engineering AP Kadapa India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

Machine Learning Research often involves the use of diverse libraries, modules, and pseudocodes for data processing, cleaning, filtering, pattern recognition, and computer intelligence. Quantization of Effort Required for the above cumulative processes is rarely discussed in the existing works and The time to reach the desired level of the model's functionality is essential to gauge the environment training for the model training and pre-deployment testing. In this study, we empirically defined the manual-cum-computational effort required for the model development in terms of 2-time factors: time-to-live (time until 1st code modification) and time-for-modification (time between 2 codebase changes) taken together in a mathematical model to compute Effort Factor(quantitative measure of determining effort needed to design ML algorithms). The study is novel in terms of how the effort required to create ML models is calculated with a particular focus on the manual effort direction. The results and the findings obtained can be used for determining the total time needed to synthesize ML models and frameworks in terms of code change cycles and implementation strategies marking a 25% performance increase in the current method above the Standard Pipeline. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Pipeline codes

来源：评论

学校读者我要写书评

暂无评论

TCIP: Transformed Colour Intensity Profiles analysis for fault detection in power line insulators

引用

Multimedia Tools and Applications 2025年第8期84卷 4503-4534页

作者： Tomaszewski, Michal Gasz, Rafal Kasana, Singara Singh Osuchowski, Jakub Singh, Simranjit Zator, Slawomir Department of Computer Science Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Prószkowska 76 Opole45-758 Poland Department of Computer Science and Information Technology Central University of Haryana Haryana Mahendergarh123031 India Department of Information Technology Dr B. R. Ambedkar National Institute of Technology Punjab Jalandhar India Department of Safety Engineering and Technical Systems Faculty of Production Engineering and Logistics Opole University of Technology Prószkowska 76 Opole45-758 Poland

In response to the escalating demand for electricity, the aging process and inherent failures in power lines have become unavoidable challenges in their operational integrity. This research addresses the imperative need for a robust method to detect damage in power insulator disc images, introducing a novel feature extraction technique grounded in color intensity profile transformation and ensemble learning. For the purposes of the research, a specific dataset was developed based on publicly available images of power insulators. The collection consists of 9232 images of insulator discs which included 2184 images of damaged discs. The discernible damages include breakages and burnouts. Two distinct analysis variants were employed. In the first variant (V1), two classification groups were selected: disc with damages and disc without damages. In the second variant (V2), three classification groups were selected: discs without damage, broken discs, and burnout discs. The described research was divided into two successive stages. In the first of them (S1), the transformed color intensity profiles for the prepared data set were built and various machine learning models for their classification were trained and evaluated. In the next stage (S2), previously developed, highest efficient machine learning models, were used to make the detection of various damaged types of overhead line insulator discs. For the first stage of research high-performance results and a high value of the F1 score parameters were obtained (F1 score = 0.999 for the first variant (S1V1) and F1 score = 0.992 for the second variant (S1V2). In the second stage of research and the first variant (S2V1), the highest result of the F1 score was 0.932 and for the second variant (S2V2) F1 score was 0.930. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

uFOIL: An Unsupervised Fusion of Image Processing and Language Understanding

引用

IEEE Access 2025年 13卷 31683-31700页

作者： Rahman, Md. Abdur Hasan, Md. Tanzimul Farooq Howlader, Umar Kader, Md. Abdul Islam, Md. Motaharul Hung Pham, Phuoc Mehedi Hassan, Mohammad United International University Department of Computer Science and Engineering Dhaka1212 Bangladesh Providence College Department of Mathematics and Computer Science ProvidenceRI02918 United States King Saud University College of Computer and Information Sciences Department of Information Systems Riyadh11543 Saudi Arabia

In academic institutions, processing and evaluating documents such as exam scripts remains a labor-intensive process susceptible to human error. Traditional digitization systems face significant challenges in handling the complexities of mixed handwritten and printed text and varying document structures. These challenges are exacerbated by the absence of annotated datasets due to privacy concerns, particularly in contexts involving sensitive exam evaluations. To address these issues, this study introduces uFOIL, an unsupervised ensemble-based framework that integrates advanced image and language processing techniques to automate the extraction and validation of key information. The framework employs a majority voting mechanism that combines four state-of-the-art optical character recognition systems. Furthermore, a transformer architecture is incorporated to enhance contextual understanding and the structured formatting of extracted text that follows a post-processing confidence scoring mechanism. The proposed framework achieves high performance, with accuracies of 95.77% and 96.48% for student names and IDs, respectively;and 95.07% for total mark validation based on a dataset of exam script samples. Additionally, experiments on the benchmark ICDAR2013 dataset suggest the framework’s strong applicability achieving precision, recall, and F1-scores of 95.89%, 97.86%, and 96.87%, respectively. © 2025 The Authors.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Classification of human-written and AI-generated sentences using a hybrid CNN-GRU model optimized by the spotted hyena algorithm

引用

Alexandria engineering Journal 2025年 126卷 116-130页

作者： Ragab, Mahmoud Ashary, Ehab Bahaudien Kateb, Faris Hakeem, Abeer Mosli, Rayan Albogami, Nasser N. Nooh, Sameer Information Technology Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Electrical and Computer Engineering Department Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia Information Systems Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

The rapid advancement of artificial intelligence (AI) in generating human-like text poses significant challenges in distinguishing between human-written and AI-generated content. Recent advancements in natural language generation have significantly enhanced the quality and variety of AI-generated text, making it almost indistinguishable from human-written content. ChatGPT, a popular AI model, belongs to the generative pre-trained transformer family. While human content is created with a clear intent to convey meaning, AI-generated text aims to replicate human-like language. Classifying human-written and AI-generated sentences is crucial for addressing issues like fake news, plagiarism, and spamming. AI text often follows repetitive patterns, while human writing is more creative and original, making detection significant for combating misinformation. Therefore, this study proposes to classify human-written and AI-generated sentences using a hybrid CNN-GRU model optimized by the Spotted Hyena Algorithm (CHWAIG-DLSHO) approach. The approach involves preprocessing text data through tokenization, lemmatization, and data splitting, followed by word embedding using Latent Dirichlet Allocation (LDA). A hybrid convolutional neural network (CNN) and gated recurrent unit (GRU) model is employed for sentence classification. The spotted hyena optimizer (SHO) model is utilized to fine-tune the hyperparameters of the CNN-GRU model, enhancing its performance. The analysis of the CHWAIG-DLSHO method takes place utilizing AI vs. human text dataset. The performance validation of the CHWAIG-DLSHO method portrayed a superior accuracy value of 99.17 % over existing techniques. © 2025 The Authors

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep neural network for emojis-based sentiment classification

引用

International Journal of Information Technology (Singapore) 2025年 1-8页

作者： Balaji, Prasanalakshmi Alsid, Linda Elzubir Gasm Sagar, Kalpna Prakasam, Shanmugapriya Department of Computer Science College of Computer Science King Khalid University Abha Saudi Arabia Department of Computer Science KIET Group of Institutions Delhi-NCR Ghaziabad India Department of Computer Science and Business Systems Rajalakshmi Engineering College Thandalam India

Sentiment classification using emojis on social media has become increasingly crucial in recent years. Social media commonly uses emojis to convey feelings, emotions, and moods. Hence, in this article, a Jellyfish Algorithm based on a Deep Convolution Neural Network (JA-DCNN) is developed for the sentiment classification of the emojis. Initially, the emoji images are collected from the open-source system. The proposed sentiment classification process uses a Jellyfish Algorithm (JA) optimized Deep Convolution Neural Network (DCNN). In DCNN, the hyperparameters are selected with the help of JA to improve accuracy and efficiency. The proposed method aims to improve the training features, maintain the resolution, reduce memory consumption, and improve the system’s accuracy. The proposed method decreases the computation cost and memory consumption, which empowers the system’s performance in emojis-based sentiment classification. The proposed method is implemented in MATLAB, and performance metrics of similarity and quality measurements evaluate performances. To validate the performance of the proposed methodology, it is compared with conventional methods such as MobilenetV2, ResNet18, and ResNet50, which have been proven to obtain better performance metrics. © Bharati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Classification Deep convolution neural network Emojis Jellyfish algorithm Sentiment analysis

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：