检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Vats, Satvik Kour, Harpreet Aggarwal, Ruchika Katoch, Navneet Sharma, Rishabh Graphic Era Hill University Graphic Era Deemed to be University Computer Science and Engineering Dehradun248002 India Chandigarh Business School of Administrations CGC Landran Department of Computer Applications Mohali India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

ISBN: (纸本)9798350370249

This study is about making a strong model to tell the difference between three popular asparagus types in India. They are called UC 157, Mary Washington, and Jersey Giant. It will be checked if it works well with Indian farming practices. The new model, made from Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks mixed, works well to correctly put asparagus types into different groups based on their unique looks. Using a very carefully picked set of 12,000 pictures, the computer does well with an overall correct rate of 96.7%. Accuracy measures like precision, recall and F 1-score show that the model is very good at telling different types apart. The rates of getting things right are over 90%. Looking at the mix-up table gives in-depth information about how well or badly the model is doing. It shows both good parts and where it could be improved better. Though the result is good, more work needs to be done. This will help make the model better at different times and places. This study shows how the developed model can be an important tool for farmers and others to accurately find out which asparagus types they have. This helps them improve their farm practices, making it easier to grow more in India's agricultural areas. © 2024 IEEE.

关键词： Livestock

来源：评论

学校读者我要写书评

暂无评论

Optimization of Hyperparameters on Migraine Classification Using Artificial Neural Networks on Human Brain's Neuronal Structure 2

Optimization of Hyperparameters on Migraine Classification U...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Singh, Kamred Udham Siddhi, Pragya Jain, Ritesh Singh, Teekam Raja, Linesh Varshney, Neeraj School of Computing Graphic Era Hill University Dehradun India G.L. Bajaj Institute of Technology and Management Uttar Pradesh Greater Noida India New Delhi India Graphic Era Deemed to be University Department of Computer Science and Engineering Dehradun India Manipal University Jaipur Department of Computer Applications Jaipur India GLA University Department of Computer Engineering & Applications UP Mathura India

ISBN: (纸本)9798350383652

The complicated network arrangement of neurons and the information processing method seen in the human brain serve as a source of inspiration for artificial neural networks. In a manner that is analogous to this configuration, artificial neurons are structured into input, hidden, and output layers. This arrangement makes it easier for data to go through the network and be processed. While Back-propagation algorithms modify weights to minimize output errors using a variety of hyperparameters, Feed Forward propagation algorithms are responsible for driving input processing via hidden layers. Appropriate activation functions are very necessary in order to successfully capture complicated nonlinear mappings between layers. One of the most important aspects of the progress that has been made in research is the experimentation with various parameters in the training of artificial neural networks. For the purpose of this paper, artificial neural networks will be trained using a variety of parameters, such as activation functions, number of layers and nodes, epochs, optimizer, batch size, and loss functions, in order to investigate the influence that these parameters have on the classification of migraine kinds by utilizing a specific dataset. By conducting an analysis of these hyperparameters, the purpose of the research is to provide information that can be used to decide which parameter combinations are the most successful for improving the results of network training. © 2024 IEEE.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Efficient Data Compression Algorithms for Cloud-Based Medical Imaging 1

Efficient Data Compression Algorithms for Cloud-Based Medica...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Sharma, Himanshu Pundir, Sumit Deepak, A. Mayuri, K. Dwivedi, Shashi Prakash Kumar, Navneet Gla University Department of Computer Engineering and Applications Mathura India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamilnadu Chennai India Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India Lloyd Institute of Engineering and Technology Greater Noida India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350330915

The storage as well as access of health-related imaging have been revolutionized by cloud-based systems. Algorithms for effective compression of information are essential for controlling the growing number of high-resolution photographs. The performance of compression techniques is assessed in this work using a deductive methodology employing a descriptive design, which is based on the interpretivist philosophy. For thorough analysis, secondary data gathering from several medical picture datasets is used. The study looks into well-known compression methodologies such wavelet-based methodologies, predictive computer programming, along with deep learning-based strategies. The results show wide variability in compression metrics, with wavelet-based techniques showing excellent spatial redundancies reduction performance. The tight equilibrium among compression overall diagnostic precision is highlighted by the slight artifacts introduced by some methods. The examination of computational resources reveals trade-offs between computing speed and memory needs, guiding real-world implementation. Statistical comparison highlights algorithmic differences and offers fact-based conclusions. The use of deep learning integration, specialized algorithm improvement, and dynamic compression methods are suggested. Future studies on telemedicine applications should investigate real-time compressing and hybrid methodologies. Data privacy and security must continue to be guided by moral and legal principles. With implications for better storage and availability for health care providers, this study enhances the field by providing an in-depth comprehension of compression algorithms within stored in the cloud medical images. © 2023 IEEE.

关键词： Compression methods CT scans data transfer medical imaging radical

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Enhanced Image Concealment: Leveraging LSB and Brotli Compression 3

Enhanced Image Concealment: Leveraging LSB and Brotli Compre...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Yacoob, Shaik Sabnis, Vikrant Jain, Jay Kumar Mansarovar Global University MP Bhopal India Mansarovar Global University Faculty of Engineering and Technology Department of Computer Science MP Bhopal India Maulana Azad National Institute of Technology Department of Mathematics Bioinformatics and Computer Applications MP Bhopal India

ISBN: (纸本)9798350354171

Steganography a cryptographic technique enables the concealment of confidential data within multimedia files like images and videos. This method facilitates the exchange of encrypted information through unconventional means, ensuring that only intended recipients can decipher the hidden message. The LSB technique has attracted significant attention in the literature due to its capability to conceal secret message bits within the least significant parts of image pixels. Although LSB has performed well in image steganography, there is some way to go in terms of its development, especially in the ways in which messages are dealt with. This paper presents a new technique of image steganography basing on the LSB method and the BROTLI algorithm. It uses the compression algorithm to compress message text. After that, to scramble the text, one LSB embedding technique is then used to hide the compressed text in the cover image. Applying the methods of data analysis on the benchmark images, the new approach developed outperforms the standard methods that exist at the present stage. This supports the idea of performing BROTLI on data with a view of compressing the data to be embedded in LSBs. © 2024 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Driven - Pest Classification and Sustainable Agriculture 3

Deep Learning Driven - Pest Classification and Sustainable A...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Kumar, M. Sirish Usha, R. Reddy, B. Rama Kantha Ramachandra, S. Prakash, P. Jaya Swetha, B. Mohan Babu University School of Computing Dept. of Data Science India Madanapalle Institute of Technology and Science Madanapalle India Sri Venkateswara College of Engineering Tirupati India Mother Theresa Institute of Engineering and Technology Palamaner India Sri Venkateswara College of Engineering Department of It Tirupati India Mohan Babu University Dept. of Master of Computer Applications India

ISBN: (纸本)9798331509675

This study introduces a system designed to identify pests in crops and classify them as either beneficial or harmful. The project begins by providing a comprehensive overview of various pest identification methods, analyzing their strengths and limitations. To address the problem, a categorization approach is proposed that incorporates convolutional neural networks (CNN) to build the pest identification and classification model. The model was trained using a dataset containing images of different pest species. Extensive testing was conducted on a large dataset, and the system's performance was validated against multiple traditional classification models. The proposed framework achieved a classification accuracy of 90%, outperforming conventional methods. This research highlights agriculture's vital role in the economy and underscores the potential of advanced technologies in supporting sustainable farming practices. © 2025 IEEE.

关键词： Agriculture Sustainability Classification Accuracy Classification Model Convolutional Neural Network (CNN) Pest Classification

来源：评论

学校读者我要写书评

暂无评论

Efficient Software Vulnerability Detection with Minimal Data Size in 5G-IoT 1

Efficient Software Vulnerability Detection with Minimal Data...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Kushwaha, Sumit Asha, V. Kumar, B Santhosh Singh, Navdeep Prabagar, S. Supriya, B Yamini University Institute of Computing Chandigarh University Department of Computer Applications Punjab India New Horizon College of Engineering Department of Computer Applications Bangalore India Institute of Aeronautical Engineering Hyderabad India Lovely Professional University Phagwara India Alliance University Alliance College of Engineering and Design Department of Computer Science and Engineering Karnataka Bangalore562106 India Koneru Lakshmaiah Education Foundation Department of Cse AP Vaddeswaram India

ISBN: (纸本)9798350359756

This research addresses the security challenges arising from the widespread implementation of Internet of Things (IoT) networks in the industry, a situation exacerbated by the integration of artificial intelligence (AI) and 5G mobile communication technologies. While these IoT networks enhance industrial efficiency and convenience, their vulnerability to security breaches is heightened due to nonstandard protocol stacks and open-source software that lacks thorough vetting. Traditional AI-based vulnerability detection methods, with their high memory and computational demands, are unsuitable for IoT applications. In response, this study introduces a novel approach utilizing the Sampling Threshold Optimization Strategy. This method maximizes the training data size while preserving learning accuracy, enabling swift identification of software vulnerabilities in IoT systems. Experiments conducted on a software vulnerability classification dataset reveal that the effectiveness of the models is not significantly impacted by variations in ideal data sizes. Notably, the research establishes the minimum amount of data required to train a model without compromising performance. For instance, employing the random forest model with the sampling threshold optimization technique resulted in a 97.9% improvement in latency and conserved 85.2% of memory, 1% of the data while still achieving learning accuracy that is on par with 100% of the data. This innovative method provides a practical means to enhance the security of IoT networks without the need for extensive processing power. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Intelligent 5G Evolution: AI-Augmented Hybrid Model with Network Slicing and Autonomous Self-Healing for Future-Ready Connectivity 3

Intelligent 5G Evolution: AI-Augmented Hybrid Model with Net...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Endla, Purushotham Pure, Ramya S. Soni, Anita Andal, C. Jagadeeswari, D. Devi, K. Nirmala Sr University School of Sciences and Humanities Department of Physics Telangana Warangal506371 India Mlr Institute of Technology Department of Computer Science and Engineering Hyderabad India Ies University Cse Department Bhopal India Dr. Mgr Educational and Research Institute Chennai India Sri muthukumaran Institute of Technology Department of Ece India Madanapalle Institute of Technology & Science Deartment of Computer Applications India

ISBN: (纸本)9798331509675

The increasing demand for dynamic, efficient, and resilient network management in 5G systems has driven advancements in AI-enhanced architectures. This research proposes an AI-Augmented Hybrid 5G Model that integrates dynamic network slicing, self-healing capabilities, and AI-driven predictive analytics to optimize network performance and reliability. The hybrid model employs supervised and unsupervised machine learning algorithms, achieving a fault detection accuracy of 95.2% and traffic demand prediction accuracy of 92.8%. Key innovations include dynamic resource allocation for enhanced mobile broadband (eMBB), ultra-reliable low-latency communications (URLLC), and massive machine-type communication (mMTC). Self-healing capabilities reduced fault recovery times to an average of 300 ms, significantly improving system uptime to 99.8%. Compared to traditional 5G systems, the model demonstrates a 50% reduction in latency, a 28.6% improvement in resource efficiency, and an 80% faster slice reconfiguration. These results highlight the model's potential to revolutionize 5G network management, ensuring reliability and adaptability for diverse applications. The study concludes by exploring the applicability of the hybrid model in future 6G networks and cross-domain orchestration. © 2025 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Data Fusion using Transfer Learning in Big Data Analytics for Healthcare 1

Multi-Modal Data Fusion using Transfer Learning in Big Data ...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

ISBN: (纸本)9798350330915

Through the use of learning transference in the framework of the analysis of large amounts of data, the present study tackles the urgent need for thorough integration of various health care information modalities. We use a descriptive study design incorporating secondary data gathering from credible healthcare sources, drawing upon an interpretivist mindset and an approach that is deductive. Medical imaging, electronic medical histories, genetic characteristics, and data from wearable sensors are just a few of the diverse data sources that are being unified by cutting-edge data preparation and integration approaches. The integrated database serves as the foundation for transfer learning, which optimizes models that were previously trained to derive insightful information. The findings show a significant improvement in the model's ability to identify complex correlations between various data kinds. The approach's precision, specificity, sensitivity, as well as AUC-ROC parameters demonstrate its efficacy. The durability and generalizability of the model across different populations of patients are further established by cross-validation methods. The contrast against benchmark approaches further emphasizes the suggested methodology's advantages in multipurpose data fusion. This work has significant clinical implications in addition to advancing healthcare data analytics. The field of medicine may undergo a revolution as a result of the enhanced diagnostic precision and individualized treatment approaches that result from the multipurpose integration of data and transferable learning, which will eventually improve the health of patients. To ensure seamless integration into standard medical environments, security of information and privacy must be taken into account. © 2023 IEEE.

关键词： data modalities healthcare medical imaging patients transfer learning

来源：评论

学校读者我要写书评

暂无评论

Investigation on Nail Denting or Crumbling from Nail Psoriasis Patient Ailment Data using the Machine Learning Algorithm and Data Mining Techniques 8

Investigation on Nail Denting or Crumbling from Nail Psorias...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Janani, K. Santhoshkumar, S.P. Vikram, D. Priya, S. Vijayaraj, M. Priyanga, M. Manipal Institute of Technology Department of Data Science and Computer Applications Manipal India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Avadi Department of Computer Science and Engineering Chennai India Rathinam Technical Campus Department of Artificial Intelligence and Data Science Coimbatore India Rathinam Technical Campus Department of Information Technology Coimbatore India

ISBN: (纸本)9798350367904

Nail denting or crumbling may result from nail psoriasis. A nail condition known as psoriatic onychodystrophy or psoriatic nails. Psoriasis sufferers frequently experience it;reported occurrences range from 10% to 78%. Psoriatic nails are more common in the elderly and in people with psoriatic arthritis. By examining the nails on a human hand, numerous illnesses can be found early in the diagnosing process. The nail color of an individual can help in the diagnosis of specific medical disorders. In this case, the recommended method results in the decision-making process for sickness diagnosis. The system is fed by human nail art. The technique recognizes nail features unique to a given condition by analyzing images of nails. The suggested technique makes advantage of the various distinctive characteristics of human nails to detect illness by changing the colour of the nails. The first training set data, which is derived from an image of a patient's nails with a particular ailment, is handled by the Weka tool. To get the desired results, the feature discoveries of the picture are compared to the training dataset. The distortion of the nail unit is known as nail disease. Nail units have their own disease class due to their own indications, symptoms, causes, and consequences, which may or may not be related to other medical disorders. Nail problems are still difficult and ambiguous to identify. A novel machine learning method for recognising and classifying nail problems from photographs is presented in this study. This framework combines CNN models with data mining techniques to extract characteristics. This research was also contrasted with certain other province algorithms (Support vector, ANN, K - nearest neighbors, and RF) evaluated on datasets and showed positive results. The accuracy numbers show how well the model can distinguish nail conditions. This ground-breaking discovery lays the groundwork for precise diagnosis in dermatology, medical image processing, an

关键词： Medical image processing

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：