检索结果-内蒙古大学图书馆

2nd International Conference on Computational Systems and Communication, ICCSC 2023

作者： Dutta, Anurag Kumar, Pijush Kanti De, Ankita Kumar, Padmanavan Dwivedi, Shubhangi Harshith, John Government College of Engineering and Textile Technology Department of Computer Science and Engineering Serampore Calcutta India Kalinga Institute of Industrial Technology Department of Computer Science and Engineering Odisha Bhubaneswar India School of Mathematical and Statistical Science Indian Institute of Technology Himachal Pradesh Mandi India Vellore Institute of Technology Department of Computer Science Tamil Nadu Vellore India

ISBN: (纸本)9781665493932

Following the recent advances in technology, came advanced computational domains like, Internet of Things, Machine Learning, Artificial Intelligence, Data science, and many more. These fields really tend to help mankind a lot. In this work, we would make use of Machine Learning aspects to perform prediction of diseases in plant. Specifically, spot the Early Blight Disease in the Potato Leaves. The potato plant, Solanum tuberosum, is a significant crop that is grown all over the world and generates large quantities of tubers that are a good source of nutrients. The potato has many medicinal benefits in addition to being a common staple diet. When the fluid out from tubers is consumed in moderation, it can treat gastric ulcers and relieve inflammation and acidity. Two harmful potato diseases, late blight and early blight, are pervasive. Everywhere potatoes are cultivated, both are present. The labels 'Early' and 'Late' allude to the relative timing of their field emergence, however both disorders might manifest simultaneously. In this work, we would focus on Early Blight. The fungus Alternaria solani, that can infect potatoes, tomatoes, several species of the potato genus, and some mustards, is the cause of early blight of potatoes. Young, actively growing plants are rarely impacted by this disease, commonly known as target spot. It first appears on elder leaves. Warm temperatures and heavy humidity foster Early Blight. This disease affects the tuber symptomized by dark, rounded to irregular dots being developed on the tuber. As the disease develops, the flesh of the potatoes commonly becomes water-soaked yellow to greenish yellow. For this work, we have collected a set of nearly 1000 samples of Early Blight affected Potato Leaves. Using that, we have modelled a Machine Learning Classification Paradigm that could potentially predict the occurrence of Early Blight Disease making using of classical classifier algorithms. Medical science have advanced to a great height.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Decoy Traffic-Aware IDS: A Novel Approach Using CSHHHNN and GGGOA

引用

IEEE Access 2025年 13卷 100791-100807页

作者： R. C. Jeyavim Sherin K. Parkavi School of Computer Science and Engineering Vellore Institute of Technology Chennai India

In the digital world, the Network Intrusion Detection System (NIDS) plays a prime role in protecting against cyber threats. Nevertheless, none of the prevailing studies focused on analyzing the impact of decoy traffic in networks, thereby resulting in poor security. To address this research gap, this article proposes a decoy traffic-aware NIDS that incorporates enhanced Cognitive Spiking Hyperbolic Hodgkin-Huxley Neural Networks (CSHHHNN) and the Greylag Griewank Goose Optimization Algorithm (GGGOA). The process starts with node initialization and registration, followed by network segmentation via clustering and subnet masking schemes. Thereafter, possible routes are recognized for each node, and then, a graph structure is generated. Next, multipath routing is established between the source and destination. Afterward, the network paths are verified. If a valid path is found, then it is selected; otherwise, it is discarded. Now, data sensing and data encryption are done. Thereafter, load balancing is performed in the encrypted data. Then, the load-balanced data is fed into the intrusion detection system. In the proposed NIDS, the dataset is initially pre-processed. Afterward, the relevant features are extracted. Subsequently, optimal features are selected, and privacy measures are applied to the model. Finally, the improved CSHHHNN model is used to classify the network traffic into normal or attack categories. The proposed approach demonstrates superior performance with 99.5124% accuracy in decoy traffic management and intrusion detection.

关键词： Feature extraction Adaptation models Telecommunication traffic Long short term memory Optimization Load modeling Bayes methods Accuracy Support vector machines Reliability

来源：评论

学校读者我要写书评

暂无评论

Enhanced Information Retrieval Using Hybrid p-Norm Extended Boolean Models with BERT

引用

Procedia computer science 2025年 258卷 3052-3061页

作者： A. Sheik Abdullah S Geetha Yeshwanth Govindarajan A G Vishal Pranav A Aashish Vinod School of Computer Science and Engineering Vellore Institute of Technology Chennai India

This paper presents an Enhanced Extended Boolean Retrieval (EBR) framework that integrates Bidirectional Encoder Representations from Transformers (BERT) to address the shortcomings of traditional retrieval models, such as Term Frequency-Inverse Document Frequency (TF-IDF), which struggle with nuanced term relationships. The approach involves fine-tuning BERT and optimizing p-Norm values to enhance retrieval accuracy and query processing. Experimental results demonstrate that the Fine-Tuned BERT with EBR achieves 92% accuracy and an Area Under the Curve (AUC) of 0.92, outperforming the TF-IDF model’s 72% accuracy and traditional p-Norm models, which achieve around 83%. This hybrid framework ofers a balanced trade-of between precision and recall, proving effective for large-scale document retrieval. The study underscores the model’s scalability and robustness, highlighting its potential to enhance Information Retrieval (IR) systems for handling complex queries across various datasets.

关键词： Information Retrieval BERT Extended Boolean Model p-Norm TF-IDF Document Retrieval

来源：评论

学校读者我要写书评

暂无评论

A deep learning model based glaucoma detection using retinal images

引用

Journal of Intelligent and Fuzzy Systems 2024年第1期1卷 1-12页

作者： Ruby Elizabeth, J. Kesavaraja, D. Ebenezer Juliet, S. Department of Computer Science and Business Systems Nehru Institute of Engineering and Technology T.M. Palayam Tamil Nadu Coimbatore India Department of Computer Science and Engineering Dr. Sivanthi Aditanar College of Engineering Tuticorin District Tamil Nadu Tiruchendur India Scope Vit Tamil Nadu Vellore India

The retinal illness that causes vision loss frequently on the globe is glaucoma. Hence, the earlier detection of Glaucoma is important. In this article, modified AlexNet deep leaning model is proposed to category the source retinal images into either healthy or Glaucoma through the detection and segmentations of optic disc (OD) and optic cup (OC) regions in retinal pictures. The retinal images are preprocessed and OD region is detected and segmented using circulatory filter. Further, OC regions are detected and segmented using K-means classification algorithm. Then, the segmented OD and OC region are classified and trained by the suggested AlexNet deep leaning model. This model classifies the source retinal image into either healthy or Glaucoma. Finally, performance measures have been estimated in relation to ground truth pictures in regards to accuracy, specificity and sensitivity. These performance measures are contrasted with the other previous Glaucoma detection techniques on publicly accessible retinal image datasets HRF and RIGA. The suggested technique as described in this work achieves 91.6% GDR for mild case and also achieves 100% GDR for severe case on HRF dataset. The suggested method as described in this work achieves 97.7% GDR for mild case and also achieves 100% GDR for severe case on RIGA dataset. AIM: Segmenting the OD and OC areas and classifying the source retinal picture as either healthy or glaucoma-affected. METHODS: The retinal images are preprocessed and OD region is detected and segmented using circulatory filter. Further, OC region is detected and segmented using K-means classification algorithm. Then, the segmented OD and OC region classified are and trained by the suggested AlexNet deep leaning model. RESULTS: The suggested method as described in this work achieves 91.6% GDR for mild case and also achieves 100% GDR for severe case on HRF dataset. The suggested method as described in this work achieves 97.7% GDR for mild case and also achie

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of IoT-Based Medicine Dispensary Box 1st

Design and Implementation of IoT-Based Medicine Dispensary B...

引用

1st International Conference on Microelectronics, Communication Systems, Machine Learning, and Internet of Things, MCMI 2020

作者： Agarwal, Disha Agarwal, Rajat Choubey, Dilip Kumar Shukla, Vaibhav School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Science and Engineering Indian Institute of Information Technology Bhagalpur Bihar Bhagalpur India Tech Mahindra Ltd Maharastra Mumbai India

ISBN: (纸本)9789811919053

The health industry and wellness sector are very crucial for the human beings and as this should be one of the important and early sectors to receive the advances of emerging technologies in the field of IoT. In the current health industry, the use of Internet of Things (IoT) makes the whole system more convenient. The Internet of Medical Things (IoMT) is also connected to IoT networks in this scenario to monitor the patients’ daily activities and to record them for future analysis. Recently, there have been many attempts to design an entirely new smart medical device which can monitor the medications of the patient and help elderly people for a better life. In this paper, we proposed an improved version of IoT-based medical medicine dispensary box. Basically, we have developed a Host Management System (HMS) which is an efficient of cloud-based installation and monitoring that stores and controls the MEDIBOX functionality for further analysis and future modification in design aspects. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Diagnosing Phytophthora infestans infestations on Solanum tuberosum leaves using Machine Learning Classifiers

Diagnosing Phytophthora infestans infestations on Solanum tu...

引用

2023 International Conference on Computational Intelligence and Sustainable engineering Solution, CISES 2023

作者： Kumar, Pijush Kanti Kumar, Indrajeet Kumar, Sanjeev Kumar, Padmanavan Harshith, John Dutta, Anurag Government College of Engineering and Textile Technology Department of Information Technology Serampore India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India G L Bajaj Institute of Technology and Management Department of Master of Computer Applications Greater Noida India Kalinga Institute of Industrial Technology Department of Computer Science and Engineering Bhubaneswar India Vellore Institute of Technology Department of Computer Science and Engineering Vellore Campus Vellore India Government College of Engineering and Textile Technology Department of Computer Science and Engineering Serampore India

ISBN: (纸本)9798350323917

In reaction to recent technology breakthroughs, modern computational fields such as the IoT, Data science, Machine Learning, AI, and several more have arisen. Humans benefit greatly from these fields. In this study, we would employ parts of machine learning to forecast plant illnesses. Particularly amongst the potato leaves, severe Late Blight Disease was discovered. The potato plant, also known as Solanum tuberosum, is a significant crop that is planted all over the world and yields copious amounts of nutritious tubers. The potato is a frequent staple food and has several health benefits. When ingested in moderation, the fluid extracted from tubers can cure stomach ulcers and reduce inflammation and acidity. Both Early and Late Blight are dangerous and widespread potato diseases. We would concentrate on Late Blight in this effort. A fatal fungus that harms potatoes is called Late Blight. It is accessible everywhere in the world. It can be found in areas of the world where potatoes are grown. Winter is the primary growing season for potatoes in India. It is followed by sweltering summer months in the lowlands. Heat and dryness kill the fungus that lives in the soil. The fungus Phytophthora Infestans, the most prevalent agricultural disease that causes the Late blight of potatoes, can quickly result in crop failure if appropriate control measures are not adopted. Potato crop declines in epidemic years might be as high as 80%. We acquired a collection of roughly one thousand samples of Late Blight-affected leaves of potatoes for this investigation. With the help of conventional classifier algorithms, we have developed a machine-learning classification paradigm that may be able to forecast the onset of Late Blight disease. Medical science has developed significantly. Plant pathology could be able to prevent the threat from happening if we could perhaps predict the illness in its early stages. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enabled Neural Networks for Intelligent Vehicle Emissions Tracking and Analysis

Cloud-Enabled Neural Networks for Intelligent Vehicle Emissi...

引用

2024 IEEE International Conference on Automation and Computation, AUTOCOM 2024

作者： Anusha, N. Jeslin, J Gnana Srividhya, V. Gupta, Nukala Sujata Meenakshi, R. Srinivasan, C. Vellore Institute of Technology School of Computer Science and Engineering Department of IoT Tamil Nadu Vellore India Rmk College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Meenakshi College of Engineering Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Chaitanya Bharathi Institute of Technology Department of Computer Engineering and Technology Hyderabad Gandipet India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350382723

A system for smart vehicle emissions monitoring and analysis using cloud computing and neural networks is presented in this paper. As global environmental concerns develop, monitoring and reducing vehicle emissions is crucial. Scalability and real-time data processing are issues for traditional approaches. Thus, cloud-enabled neural network architecture for scalable and efficient vehicle emissions monitoring using distributed computing is developed. A neural network model trained on various vehicle emission datasets, allowing for precise pattern analysis and prediction of emissions. The scalability of the system is guaranteed by using cloud resources, which can accommodate the rising amount of data created by an increasing number of vehicles. By incorporating cloud-based data processing seamlessly, real-time monitoring is accomplished, enabling immediate analysis and prompt emission alerts. The suggested emissions tracking platform is robust and scalable to intelligent transportation systems by revealing vehicle emissions' environmental effect. Future smart city and sustainable urban transportation developments are built on cloud computing and neural networks. The proposed system shows how cloud-enabled neural networks may solve complicated vehicle emissions problems. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Elevating IDS Capabilities: The Convergence of SVM, Deep Learning, and RFECV in Network Security

Elevating IDS Capabilities: The Convergence of SVM, Deep Lea...

引用

Emerging Trends in Information technology and engineering (ic-ETITE), Conference on

作者： G Aditya Kumar Aditi Katiyar Kathiravan Srinivasan Computer Science Engineering Vellore Institute of Technology Vellore India School of Computer Science and Engineering Vellore Institute of Technology Vellore India

By presenting an improved Intrusion Detection System (IDS) that combines deep learning with support vector machines (SVM), this research increases network security. The main goal is to increase the accuracy of SVM detection by using a methodical feature selection and optimization technique that is tailored to the complexity of network intrusions. 35 out of the 42 features were chosen for feature selection using RFECV, an algorithmic feature selection technique in machine learning. To ensure that the features preserved are those that contribute most to the model's predictive capacity and that the redundant features are deleted, techniques such as RFECV and feature priority ranking using ExtraTreesClassifier take the model's performance into account during the feature selection process. To improve classifier performance, optimization strategies such as hyperparameter tuning are used, focusing on important data and cutting down on redundancies. The performance of several SVM kernel functions, including linear, polynomial, RBF, and sigmoid, is compared in the study. The Linear model combined with the deep learning model was shown to perform the best. Our model outperforms current IDS frameworks, as demonstrated by comparative analysis, confirming the efficacy of integrating SVMs with deep learning for real-time threat detection. The KDD Cup 99 dataset, which has been widely used as a benchmark for assessing the performance of different IDS models, was used for the work. It offers a consistent, varied, and large dataset so that researchers may evaluate and contrast their methods. Researchers can experiment with feature selection and reduction strategies to enhance IDS performance because of the dataset's broad set of features.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shape Organization for Enhanced Design Optimization in Generative Systems Using Clustering technology 6

Shape Organization for Enhanced Design Optimization in Gener...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Krishna, Raji Suganya, R. Yaganti, Mounika Sai Mohamed Buhari, Seyed Vellore Institute of Technology School of Electrical Engineering Chennai Campus Chennai India Vellore Institute of Technology School of Computer Science Engineering Chennai Campus Chennai India University Brunei Darussalam Department of Computer Science Gadong Brunei

ISBN: (纸本)9798350394702

The current research in design space articulation tries to solve the problem that comes up because computer generative systems are becoming more complex, and there are more design options. This study makes a contribution to the existing body of research by introducing a technique for form clustering that utilizes K-medoids, a Machine Learning approach. The suggested method uses a clustering method to group design shapes that are similar and then pick a representative body for each cluster in a 2D-Grid Based representation. The efficacy of the process has been empirically validated by applying it to a novel test case and comparing it with other clustering evaluation methods. The accuracy of the results of this evaluation is about the same as that seen in an outside study. This gives us essential information about how to judge machine learning techniques. © 2023 IEEE.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

An Energy Efficient Hybrid Communication Protocol for Large Area Wireless Sensor Networks

引用

Procedia computer science 2025年 252卷 985-994页

作者： Shreyas Karthigeyan Sampark Bhol Akshat Jain Karthik Yadav Akash Sinha Padma Priya R School of Computer Science and Information Systems Vellore Institute of Technology Vellore Campus Vellore Tamil Nadu 632014 India School of Computer Science and Engineering Vellore Institute of Technology Vellore Campus Vellore Tamil Nadu 632014 India Department of Computer Science and Engineering Maulana Azad National Institute of Technology Bhopal Madhya Pradesh 462003 India

Energy conservation is an indispensable aspect of the protocols designed for Wireless Sensor Networks (WSNs). The communication protocols for WSN fall mainly under two categories: centralized and distributed. Centralized protocols are not feasible for real-world WSNs as the network can span across large areas where most of the nodes cannot directly communicate with the base station (BS). The routing issues in such networks can be addressed using multi-hop protocols. However, the process of BS guided clustering in such methods cannot be performed. Distributed clustering methods that minimize the intervention of BS in clustering can provide feasible solutions in such cases, but the energy expenditure is considerably high. This paper, hence, proposes a hybrid clustering based routing protocol for large WSN that employs certain aspects of centralized as well as that of distributed protocols. Experimental evaluation of the proposed protocol in terms of network lifetime gives promising results that clearly indicate the energy efficiency and consistency of the proposed work in different scenarios. The proposed work can prove beneficial in real-life scenarios where the deployed nodes are far away from the BS.

关键词： WSN Hybrid Cluster Multi-Hop Energy

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：