检索结果-内蒙古大学图书馆

Deep analysis of MFCC and MEL spectrogram features to recognize and classify stuttered speech

Multimedia Tools and applications 2025年 1-20页

作者： Banerjee, Nilanjan Sethi, Nilambar Borah, Samarjeet Department of Computer Science and Engineering GIET University Odisha India Department of Computer Applications Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim India

Human thoughts, feelings, and ideas are expressed through speech. Stuttering, also referred to as stammering, is an impediment to speech that affects millions of people across the globe. Stuttering speech recognition is a good deal of research within the realm of speech signal processing. Classification of eight different types of stuttering including fluent, interjections, broken words, prolongations, word repetitions, phrase–repetitions, part-word repetitions, and sound repetitions is the main motivation in this research. Stuttering speech recognition is becoming easier with the advancement of machine learning and deep learning. The present study focuses on the efficacy of stuttering speech recognition through the application of machine learning & deep learning. Analysis in this study began with traditional machine learning algorithms, such as Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). It is seen, feature extraction is an essential component in achieving accurate classification for machine learning algorithms. MFCC & MEL spectrogram features are extracted for this experiment. Furthermore, Delta2 MFCC and Delta2 Mel Spectrogram are derived by second-order derivatives on MFCC & Mel Spectrogram features. Therefore, a variety of these features are employed as input to the model. In comparison with all the aforesaid traditional machine learning models, the KNN model results in the highest accuracy of 69.1% based on MFCC-40 input features. To improve accuracy, we move to a deep learning approach. In this experiment, the convolutional neural network (CNN) model produces better outcomes than traditional machine learning. The study presents a comprehensive analysis of the CNN model with MFCC & MEL spectrogram features, as well as its efficiency. It is noted that MFCC-40 input features in CNN model results in the highest accuracy of 89% after 400 epochs. © The Author(s), under exclusive licence to Springer science+Bus

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Algoviz—Real-Time Insight of Algorithms 3rd

Algoviz—Real-Time Insight of Algorithms

引用

3rd International Conference on Emerging Trends in Expert applications and Security, ICE-TEAS 2024

作者： Prasad, S. Ashwini Hanumanthappa, M. Supriyaa, K. Rathore, Vijay Singh Department of Computer Science and Applications Bangalore India Department of Computer Science Engineering Jaipur India

ISBN: (纸本)9789819737444

Algorithms are central objects of every nontrivial computer application but their analysis and design are a great challenge. While traditional methods involve mathematical and empirical approaches, there exists a third avenue for studying algorithms, i.e. the algorithm visualizer. Algorithm visualizer is an interactive software tool designed to enhance the understanding and learning of various algorithms through visual representation. This tool provides a dynamic and engaging way to explore complex computational processes, making them more accessible to both novice learners and experienced programmers. The visualization platform offers a diverse range of algorithms, spanning data structures, sorting methods, graph traversal techniques, path finding algorithms, and more. Through real-time interaction, users gain insights into algorithmic operations, fostering a deeper understanding of their logic and behaviour. Users can customize inputs, experiment with different scenarios, and observe, how algorithmic choice impacts outcomes in a visual and interactive manner. The primary goal of algorithm visualizer is to elucidate the inner workings of various known algorithms by presenting them graphically, thereby simplifying their complexities for comprehension. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： computer debugging

来源：评论

学校读者我要写书评

暂无评论

Enhancing thyroid disease prediction with improved XGBoost model and bias management techniques

引用

Multimedia Tools and applications 2025年第16期84卷 16757-16788页

作者： Dalal, Surjeet Lilhore, Umesh Kumar Faujdar, Neetu Simaiya, Sarita Agrawal, Akshat Rani, Uma Mohan, Anand Department of Computer Science and Engineering Amity University Haryana Gurugram India Department of Computer Science and Engineering Galgotias University Uttar Pradesh Greater Noida India Department of Computer Engineering and Applications GLA University Uttar Pradesh Mathura India Department of Computer Science & Engineering Amity University Haryana Gurugram India Department of Computer Science and Engineering World College of Technology & Management Haryana Gurugram India Department of Physics Kunwar Singh College Bihar Darbhanga India

The thyroid gland, a pivotal regulator of essential physiological functions, orchestrates the production and release of thyroid hormones, playing a vital role in metabolism, growth, development, and overall bodily functions. While thyroid nodules are predominantly benign, certain cases may manifest malignancy, leading to thyroid cancer. Despite the generally favorable prognosis, early detection and intervention remain paramount for optimal outcomes. Given the limitations in clinical data, this paper introduces an innovative approach employing a modified XGBoost model that integrates both clinical and molecular properties into a unified predictive model. Utilizing fine-needle aspiration biopsies and gene expression analysis, our model aims to enhance cancer prediction in thyroid nodules. We explore the influence of incorporating high-quality clinical data on the prioritized gene set, employing a nature-inspired method for hyperparameter optimization. The modified XGBoost model emerges as highly recommended for non-parametric feature selection, extraction, and prediction due to its remarkable accuracy. Our proposed model attains an impressive 94.6% accuracy, surpassing other machine learning models such as C5.0 (92.5%), CART (88.7%), CHAID (83.4%), Quest (81.5%), LSVM (77%), and random tree (24.1%). The real-time efficiency of our model is demonstrated in the results section. Experiments showcase the superior performance of combined molecular and clinical data-based prediction models. Emphasis is placed on the importance of scrutinizing the origins of clinical data and maintaining vigilance over variable quality. This study signifies a substantial advancement in thyroid cancer prediction, offering a robust and accurate model that integrates diverse data sources, ultimately contributing to improved patient outcomes. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Aggregated Relative Similarity (ARS): a novel similarity measure for improved personalised learning recommendation using hybrid filtering approach

引用

Multimedia Tools and applications 2025年第18期84卷 18733-18780页

作者： Pal, Saurabh Dutta Pramanik, Pijush Kanti Choudhury, Prasenjit Department of Computer Science and Engineering National Institute of Technology Durgapur West Bengal Durgapur India School of Computer Applications and Technology Galgotias University Uttar Pradesh Greater Noida India Department of Computer Science and Engineering School of Engineering Brainware University Kolkata India

To improve the effectiveness of online learning, the learning materials recommendation is required to be personalised to the learner material recommendations must be personalized to learners. The existing approaches are ineffective in recommending learning materials according to the learner’s learning situation, the learner’s internal learning characteristics, and fitting to the learner’s preferences and learning suitability. In this work, we propose a hybrid recommendation approach cthat combines the advantages of knowledge-based and collaborative filtering approaches. The knowledge-based filtering approach enables us to find the most suitable learning materials that fit the learner’s situation and learning state by appropriately mapping the learners’ contexts with the metadata of the learning materials. We use collaborative filtering to refine learning material selection by considering learner-learner similarity. We propose a novel similarity measure, aggregated relative similarity (ARS), to determine similar learners based on implicit learner characteristics such as education, knowledge, cognitive ability, and learning style. The experimental results show that the proposed ARS algorithm outperforms popular similarity measures such as Jaccard similarity, Sorensen-Dice coefficient, and overlap coefficient. The overall recommendation performance of the proposed hybrid approach attained mean absolute error (MAE) and root mean square error (RMSE) of 0.681 and 0.9198, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Research on Internet of Medical Things: Systematic Review, Research Trends and Challenges

引用

Recent Advances in computer science and Communications 2024年第6期17卷 72-82页

作者： Anand, Dinesh Kaur, Avinash Singh, Manpreet School of Computer Applications Lovely Professional University Punjab Phagwara India School of Computer Science and Engineering Lovely Professional University Punjab Phagwara India Department of Computer Applications Guru Nanak Dev Engineering College Punjab Ludhiana India

Introduction: Remote data exchange operations in healthcare are observed, consult-ed, monitored and treated by the Internet of Medical Things (IoMT). It is an extension of the Internet of Things (IoT). Method: At the growing stage of IoT, IoMT is speedily drawing researchers’ interest due to its extensive use in healthcare systems. Smaller and lower-priced wireless devices with various communication protocols have led to the formation of IoMT. Healthcare data is exchanged through wireless communication with IoMT. The margining of IoMT and healthcare can yield multiple benefits in terms of: better quality of life, care services and developing solution/s at low cost. In this article, a systematic literature review has been conducted on IoMT. Results: Authors have thoroughly investigated the different versions of healthcare 1.0, 2.0, 3.0 and 4.0 as proposed by the healthcare industry. Furthermore, the taxonomy of IoMT has been designed and compared with existing surveys. Conclusion: This survey is unique and stands different from the point of view of existing sur-veys. It supports the future of IoMT researchers to bring new insight to their researches. © 2024 Bentham science Publishers.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

A Novel Eccentric Intrusion Detection Model Based on Recurrent Neural Networks with Leveraging LSTM

引用

computers, Materials & Continua 2024年第3期78卷 3089-3127页

作者： Navaneetha Krishnan Muthunambu Senthil Prabakaran Balasubramanian Prabhu Kavin Kishore Senthil Siruvangur Kavitha Chinnadurai Jehad Ali Department of Computer Applications Karpagam College of EngineeringCoimbatore641032India Department of Computer Science and Engineering Karpagam College of EngineeringCoimbatore641032India Department of Data Science and Business Systems College of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur603203India Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyJeppiaar NagarRajiv Gandhi SalaiChennai600119India Department of AI Convergence Network Ajou UniversitySuwon16499Korea

The extensive utilization of the Internet in everyday life can be attributed to the substantial accessibility of online services and the growing significance of the data transmitted via the ***,this development has expanded the potential targets that hackers might *** adequate safeguards,data transmitted on the internet is significantly more susceptible to unauthorized access,theft,or *** identification of unauthorised access attempts is a critical component of cybersecurity as it aids in the detection and prevention of malicious *** research paper introduces a novel intrusion detection framework that utilizes Recurrent Neural Networks(RNN)integrated with Long Short-Term Memory(LSTM)*** proposed model can identify various types of cyberattacks,including conventional and distinctive *** networks,a specific kind of feedforward neural networks,possess an intrinsic memory *** Neural Networks(RNNs)incorporating Long Short-Term Memory(LSTM)mechanisms have demonstrated greater capabilities in retaining and utilizing data dependencies over extended *** such as data types,training duration,accuracy,number of false positives,and number of false negatives are among the parameters employed to assess the effectiveness of these models in identifying both common and unusual *** are utilised in conjunction with LSTM to support human analysts in identifying possible intrusion events,hence enhancing their decision-making capabilities.A potential solution to address the limitations of Shallow learning is the introduction of the Eccentric Intrusion Detection *** model utilises Recurrent Neural Networks,specifically exploiting LSTM *** proposed model achieves detection accuracy(99.5%),generalisation(99%),and false-positive rate(0.72%),the parameters findings reveal that it is superior to state-of-the-art techniques.

关键词： Cybersecurity intrusion detection machine learning leveraging long short-term memory(LLSTM) CICIDS2019 dataset innovative cyberattacks

来源：评论

学校读者我要写书评

暂无评论

An Intelligent System to Predict Diabetic Retinal Diseases Based on Diabetic Attributes

引用

SN computer science 2024年第6期5卷 755页

作者： Eswari, M. Shanmuga Balamurali, S. Ramkumar, K. Department of Computer Applications Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Rajalakshmi Institute of Technology

The most common illness among individuals and the general population in the medical field is diabetes. This is coupled with a careful diabetic retinal that has no signal. The historical record offers unrecoverable insight. To avoid a hallucinatory dispute at the time, early detection of retinal illness is necessary. Positively, the results of diabetic patients have been able to foretell the threat of diabetic-related eyeailments such as Diabetic Retinopathy, Glaucoma, and Diabetic Macular Edema.A diabetic retinal disease prediction exemplary have been created by via system learning rules, such as narrow neural network, bilayered neural network, wide neural network and trilayer neural network, in close proximity to the onset of the disease. The trilayer neural network with various activation functions accuracy based results servedas the foundation for the final model that evaluates real time data to predict the likelihood of *** learner representation accuracy of 0.95and the evaluation phase accuracy of 0.94 are *** ideal diabetic features-based diabetic retinal system outcome occupies a crucial place in the medical decision support system to make prompt assessments in the field of E-healthcare system to connect ophthalmology field to eradicate insulin based eye problems at the time of regular assessment. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Boosting computer-aided Design Diabetic Mellitus Ensemble Machine Learner Retinal eye Disease

来源：评论

学校读者我要写书评

暂无评论

A Secure Healthcare Monitoring System for Disease Diagnosis in the IoT Environment

引用

Multimedia Tools and applications 2025年第7期84卷 3767-3792页

作者： Verma, Ankit Gupta, Amit Kumar Kumar, Vipin Rajak, Akash Kumar, Sushil Panda, Rabi Narayan Department of Computer Applications KIET Group of Institutions Delhi-NCR Ghaziabad India Computer Science & Engineering KIET Group of Institutions Ghaziabad Delhi-NCR India

People who lead hectic lives daily suffer from a variety of illnesses, including diabetes, high blood pressure, hypertension, etc. For someone to survive, they must become aware of these illnesses promptly. The Internet of Things (IoT) and cloud computing are the two critical prerequisites for digital healthcare. In the present research, the attacked data are detected and removed using the security module to enhance the security of the healthcare system. However, an accurate prediction mechanism is needed for the early diagnosis of the diseases. To predict the sickness and its severity more accurately, a unique Dragon Fly-based Generalised Approximate Reasoning Intelligence Control (DF-GARIC) is devised in this article. This system was primarily responsible for preprocessing the cloud medical records entered into the system. Additionally, the regression algorithm extracts the relevant features. Based on the retrieved features, the dragonfly function is used to classify the disease and estimate its severity. Subsequently, a warning is given to the providers for the abnormal condition via SMS or e-mail. The system validated a higher accuracy level of 99.8% from the MATLAB execution. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Visualizing the Impact of Machine Learning on Cardiovascular Disease Prediction: A Comprehensive Analysis of Research Trends

Scientific Visualization

引用

Scientific Visualization 2024年第5期16卷 1-21页

作者： Joseph, Jeena Kartheeban, K. Department of Computer Applications Kalasalingam Academy of Research and Education Tamilnadu Krishnankoil India Department of Computer Applications Marian College Kuttikkanam Autonomous Idukki Kerala India Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil Tamilnadu India

Cardiovascular diseases (CVDs) continue to have a negative impact on global health, which highlights the need for accurate and efficient prediction methods. Machine learning (ML) techniques as tools for forecasting CVD has recently showed potential. This paper presents a comprehensive analysis of research trends in the field, focusing on visualizing the impact of ML in cardiovascular disease prediction. We used data visualization techniques to identify patterns and trends in an extensive database of scholarly publications on this subject that were published in Scopus between 1991 and 2023. The analysis reveals a substantial growth in research output, demonstrating the growing demand for ML-based CVD prediction. It reveals essential stakeholders and potential collaborators while highlighting the institutions and authors who have contributed most to this domain. The study also identifies high-impact journals that have published significant research in this domain, facilitating researchers in selecting appropriate outlets for dissemination. The study helps researchers identify the most critical areas for further research and fosters cooperation among subject-matter experts by offering insightful information about machine learning-based cardiovascular disease prediction development. The data is analyzed using the tools VOSviewer and Biblioshiny. © 2024 National Research Nuclear University. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Predictive Autoscaling for Containerized applications Using Machine Learning 1

Predictive Autoscaling for Containerized Applications Using ...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Mogal, Amit K. Sonaje, Vaibhav P. School of Computer-Science and Engineering Sandip University Department of Computer Science & Applications Nashik India

ISBN: (纸本)9798350361780

As containerization continues to gain prominence in modern application deployment, the need for efficient autoscaling mechanisms becomes paramount to ensure optimal resource utilization and adherence to service level objectives. This research paper proposes a Predictive Auto-scaling framework leveraging machine-learning(ML) techniques to anticipate and proactively adjust the resources allotted to containerized applications. The aim is to enhance the scalability and responsiveness of applications running in dynamic and cloud-native environments. An auto-scaling technique with burst awareness for containerized applications is proposed in this research. This innovative method optimizes container utilization while meeting the Quality-of-Service requirement by taking into account a mix of both vertical and horizontal skills. The proposed proactive autoscaling strategy addresses the challenges posed by unpredictable workloads and varying application demands, fostering adaptability to dynamic environments. By highlighting the significance of machine learning in improving the predictability and effectiveness of resource scaling for containerized systems, this study adds to new work of research on auto-scaling methodologies. © 2024 IEEE.

关键词： Containers

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：