检索结果-内蒙古大学图书馆

1st Asian Conference on Communication and Networks, ASIANComNet 2024

作者： Ayyalasomayajula, Madan Mohan Tito Mandala, Vishwanadham Prasad, Hanumat Gangopadhyay, Amit Shrivastava, Neeraj Sundaram, Ajith Aspen University School of Business & Technology Department of Computer Science Arizona United States Cummins Inc. IN United States Department of CSE- AI&ML Guntur India Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College Department of Electronics and Communication Engineering Andhra Pradesh Tirupati India Medicaps University Indore India Amrita Vishwa Vidyapeetham Amrita Nagar Edappally Amrita School of Business Kochi Kerala Ernakulam India

ISBN: (纸本)9798350367003

The Internet of Things (IoT) is a network that connects a vast number of objects, enabling them to communicate and interact with each other with human intervention. The IoT is seeing rapid growth in the field of computing. However, it is important to acknowledge that IoT is very susceptible to many forms of assaults due to the hostile nature of the internet. In order to address this problem, it is necessary to implement practical steps to ensure the security of IoT networks, such as the implementation of network anomaly detection. While it is impossible to completely prevent assaults indefinitely, timely discovery of an attack is essential for effective defense. Because IoT devices have limited storage and processing power, standard high-end security solutions cannot protect them. In addition, IoT devices are now autonomously linked for extended durations. Consequently, it is necessary to create advanced network-based security solutions such as deep neural network solutions. While several researches have focused on the use of neural network methods for attack detection, there has been less emphasis on detecting assaults, especially in IoT networks. The objective of this research is to develop a gradient clipping long shortterm memory network (GC-LSTM) that can efficiently and promptly identify IoT network assaults. The Bot-IoT dataset is employed for evaluating various detection methodologies. The incorporation of additional features resulted in improved results. The GC-LSTM model, as proposed, achieves a remarkable accuracy of 99.98%, 97.67% of detection rate, 87.34% of TNR and 34.67% of FAR. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach to Data Clustering Using the K-Means Algorithm in Big Data Analytics

An Efficient Approach to Data Clustering Using the K-Means A...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： S. Sandhiya Vani Ramya P Y. Nagendar P. Arun Prakash Malladi Chanti Athiraja Atheeswaran Department OF Computer Science and Engineering Rajalakshmi Engineering College Chennai Department of Computer Science and Engineering Anna University University College of Engineering Department of School of Computer Science and Artificial Intelligence SR University Hyderabad Telangana Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Computer Science and Engineering Malla Reddy Engineering College (Autonomous) Hyderabad Telangana Department of CSE(AI&ML) Malla Reddy College of Engineering Hyderabad Telangana India

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

The large-scale, high-dimensionality of datasets poses major obstacles to effective and precise data clustering in the field of big data analytics. This work focuses on a well-known technique for dividing huge datasets into informative clusters: the K-Means algorithm. This approach to data clustering is efficient. However, because of scalability and computational complexity problems, K-Means is not as effective when managing large amounts of data. In order to reduce processing cost and improve clustering accuracy, this work provides an improved version of the K-Means algorithm that blends dimensionality reduction approaches and efficient initialization methods. Principal Component Analysis (PCA) is used as a preprocessing step in the methodology to reduce the dimensionality of huge datasets. An optimized K-Means algorithm with improved centroid initialization is then applied. These changes lead to shorter iteration durations and higher-quality clusters. Comparing the results to standard K-Means, experiments on many big data benchmarks showed a 15% gain in cluster accuracy and a 25% reduction in execution time. To sum up, the incorporation of optimized initialization techniques and dimensionality reduction greatly improves the scalability and performance of K-Means in big data analytics, with useful implications for sectors that depend on effective data analysis.

关键词： Dimensionality reduction Accuracy Scalability Supervised learning Clustering algorithms Big Data Data models Classification algorithms Standards Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

An Efficient Method for Smart Parking System Using Adaptive CNN Ensemble Approach

An Efficient Method for Smart Parking System Using Adaptive ...

引用

International Conference on Inventive Research in Computing Applications (ICIRCA)

作者： R. Ganesh B. Srinivasa Rao Sreemayi Goriparthi Priyank Udaybhai Trivedi Neerav Nishant P Naresh Kumar Reddy Computer Science and Engineering (AI&ML) Institute of Aeronautical Engineering Hyderabad Telangana India Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad Telangana India Department of Computer Science and Engineering (AI&ML) Guru Nanak Institute of Technology Ibrahimpatnam Telanagana India Institute of Infrastructure Technology Research and Management Maninagar Ahmedabad Gujarat India Department of Computer Science and Engineering School of Engineering Babu Banarasi Das University Lucknow Uttar Pradesh India Department of Freshman Mohan Babu University Tirupathi India

Every big city across the world has a similar parking problem: it's expensive and hard to find. There is an immediate need for creative parking solutions to fulfill the anticipated parking demand. Using encrypted wireless networks and sensor data, this article suggests an advanced new parking system called Smart Parking. Smart Parking provides a safe and smart parking environment for its customers. The allocated parking spot is secure and discrete. The parking guidance system works well and is easy to use. Every step of the parking procedure will be offered continuously. Smart parking is an advanced parking management system from the perspective of the administration. The suggested method involves a series of steps, including preprocessing, DHE for contrast enhancement, CHT for feature extraction, and Adaptive CNN Ensemble for model training. The proposed method has better results than the other two models (CNN and SVM).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Eyecheck Diabscan: A Productive Approach for Few-Shot Excellence in Retinopathy Diagnosis

Eyecheck Diabscan: A Productive Approach for Few-Shot Excell...

引用

Advanced Computing & Communication Technologies (ICACCTech), International Conference on

作者： Nuthanakanti Bhaskar E. Krishnaveni Sinde Jayavanth Rao Kumbala Pradeep Reddy G Vinoda Reddy Avala Raji Reddy Department of Computer Science and Engineering CMR Technical Campus Hyderabad India Department of Computer Science and Engineering CMR College of Engineering & Technology Hyderabad India Department of Computer Science and Engineering (DS) CMR Engineering College Hyderabad India Department of Computer Science and Engineering CMR Institute of Technology Hyderabad India Department of Computer Science and Engineering (AI&ML) CMR Technical Campus Hyderabad India Department of Mechanical Engineering CMR Technical Campus Hyderabad India

ISBN: (数字)9798331519056

ISBN: (纸本)9798331519063

The design and implementation of a few-shot learning-based diabetic retinopathy diagnostic system is the focus of this research project. According to the NEI (National Eye Institute), The United States report 2021, diabetic retinal degeneration is one of the most common causes of vision loss in people aged 20 to 74. Early recognition and treatment are therefore deemed essential. The National Eye Institute is a resource-based informational center about diseases and eye health. The primary objective of this endeavor is to improve the few-shot learning technique's capacity for early-stage diabetic eye disease detection. This suggested model may operate using a restricted amount of data, i.e., less data processing by enhancing data optimizing, and localize the necessary discriminative regions. Additionally, it enables the model to recognize and follow unique, novel patterns among the inputs. This approach is going to operate along with an assessment of proposals pertaining to patients' geographic and financial obstacles. Diabetic Retinopathy Identification is applied in the medical and healthcare sectors. This enables us to manage progression risk, forecast therapy results, and lessen adverse consequences and acute implications.

关键词： Diabetic retinopathy Accuracy Shape Shape measurement Retina Pattern recognition Ophthalmology Proposals Few shot learning Recommender systems

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Power Metering Automation for Improving data Integrity and Reliability in Power Marketing Meters

IoT-Based Power Metering Automation for Improving data Integ...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Samreen, Sumaiya Chanti, Yerrolla Mounika, P. Mandava, Manjusha Kruthika, C.G. Malla Reddy Engineering College for Women It Department Hyderabad India Sr University School of Computer Science & Artificial Intelligence Warangal India Hyderabad India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

The goal of this paper is to provide an internet of things (IoT)-based approach for automated electricity metering. When measuring power using standard methods, inaccuracies and erroneous readings are possible, putting the data's integrity and authenticity at risk. The suggested method employs sensors linked to the internet of things (IoT) and machine learning algorithms to detect abnormalities and inconsistencies in real-time energy use statistics. This was evident during the testing phase. The proposed method offers several benefits over the present standard of power metering systems in use. The testing findings demonstrated that the proposed system is more reliable and effective in terms of 0.957 success rate, 0.943 accuracy, 0.967 recall, 0.956 F1 score and 0.982 AUC. © 2023 IEEE.

关键词： Anomaly detection Cloud-based data storage and analysis platform Internet of Things (IoT) Machine learning algorithm Power metering Real-time data analysis User interface

来源：评论

学校读者我要写书评

暂无评论

EAP Based Certificateless Authentication Technique to Access Cloud Services in Openstack 8th

EAP Based Certificateless Authentication Technique to Access...

引用

8th International Conference on Cognition and Recognition, ICCR 2021

作者： Raghavendra, K. Ramesh, B. Chandrika, J. Computer Science and Engineering AI-ML Department Dayananda Sagar University Kudlu Gate Hosur Main Road Karnataka Bangalore560068 India Department of Computer Science and Engineering Malnad College of Engineering Karnataka Hassan India

ISBN: (纸本)9783031224041

Nowadays cloud services have gained more interest. The main advantage of the cloud is, it reduces management costs and efficient usage of resources. The major role of efficient authentication means not only providing authentication but it should also reduce the authentication traffic and provide security. There are many authentication mechanisms most of them were only for a web application. Here in this paper, we focus on both web and non-web applications authentication in cloud environment to access SaaS service. For non-web application services of cloud, ABFAB has created an architecture. ABFAB also defines how to use existing EAP/AAA and GSS-EAP for both web and non-web-based applications. In this paper, we mainly focus on efficient AAA to access cloud services. To demonstrate the proposed system, we use the moonshot from Github, freeradius an opensource, and Openstack for cloud service with our proposed authentication method. We have done the performance analysis of our authentication method compared with the other authentication mechanism to access cloud services. This analysis shows a significant reduction in the computation time required for authentication and reduction in the authentication traffic. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Examination System Automation Using Natural Language Processing

Examination System Automation Using Natural Language Process...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： R Praveen Kumar N. Muthukumaran Cheruku Hanisha Pohar Rithvik M.Saipavan Goud Department of Computer Science and Engineering (AI&ML) Vignan Institute of Technology and Science Department of ECE Centre for Computational Imaging and Machine Vision Sri Eshwar College of Engineering Coimbatore Tamil Nadu India

Numerous examination portals have been created and distributed over several servers for a number of objectives, including the administration of tests in connection withadmission exams, Olympic competitions at national and worldwide levels, and the administration of placement tests. It turns out that practically all portals are set up for multiple-choice examinations, as we found. Our goal here is not to work on current technology, but rather to work on technology that is very uncommon. The descriptive online examination method is discussed here. Simple to use, multiple choice questions are composed of a question, many possible answers to the same question as well as a field to record the correct response in the database. Descriptive queries, on the other hand, do not fall within this category. To award marks to replies, it incorporates or employs Natural Language Processing (NLP) ideas. The model's responsibility is to lead procedure on the response string so it can give the right stamps to the examinee's responses. The data is generally assembled utilizing an enlightening web-based appraisal procedure. It is likewise inspected, and the made model honors right stamps to the inquiry's answers. With respect to the front-end, HTml 5, CS S 3, Bootstrap, and JavaS cript are utilized. The back-end was created in Python using Django, NLTK for Natural Language Processing, and SQLite version 3 as the database.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion of Convolutional Neural Networks and Random Forests for Accurate Potato Leaf Disease Detection

Fusion of Convolutional Neural Networks and Random Forests f...

引用

Applied Intelligence and Computing (aiC), IEEE World Conference on

作者： Durgunala Ranjith Bhargav Somisetty Sallauddin Mohmmad P Ramana Jayapal Lande School of Computer Science and Artificaial Intelligence SR University Warangal Telangana India Department of CSE(AI&ML) CVR College of Engineerning Hyderabad Telangana India Computer Science and Engineering Hyderabad Institute of Technology and Management Hyderabad Telangana India

ISBN: (数字)9798350384598

ISBN: (纸本)9798350384604

In order to classify potato leaf diseases, this work suggests a hybrid model that combines a Random Forest classifier for sample class classification with a CNN for image feature extraction. The dataset obtained from Kaggle includes 1885 samples of different potato leaf illnesses caused by fungi, viruses, pests, bacteria, Phytophthora, nematodes, and healthy leaves. Thorough preprocessing entails dividing the dataset into equal training, testing, and validation sets and downsizing photos to a standard dimension. The CNN model uses ReLU activation for normalization and softmax activation for classification. It has five layers with progressively larger filter sizes. For the final label classification, features taken from the CNN are fed into a Random Forest classifier consisting of 100 decision trees. The suggested model shows promise in terms of performance and accuracy in classifying diseases. The hybrid model suggested for classifying diseases affecting potatoes shows encouraging results; it has an overall accuracy rate of 77% and a precision range of 44% to 96% for various disease categories.

关键词： Training Accuracy Computational modeling Crops Convolutional neural networks Random forests Standards Optimization Diseases Testing

来源：评论

学校读者我要写书评

暂无评论

ARIA: Augmented Reality and Artificial Intelligence enabled mobile application for Yield and grade prediction of tomato crops

引用

Procedia computer science 2024年 235卷 2693-2702页

作者： Balaji Prabhu B V Shashank R Shreyas B Omkar Subbaram Jois Narsipura Dept. of Computer Science and Engineering (AI&ML) Malnad College of Engineering Hassan Visvesvaraya Technological University Belagavi India 573202 Dept. of Computer Science Viterbi School of Engineering University of Southern California Los Angeles USA 90007 Dept. of Computer Science and Engineering RNS Institute of Technology Bangalore India 560098 Dept. of Aerospace Engineering Indian Institute of Science Bangalore India 560012

Agriculture is the most crucial sector of the Indian economy. Lately, there has been a surge in the usage of technologies like deep learning and computer vision to make the process of agriculture modern and consequently, lessening the mistakes related to conventional processes. This work delivers a user-friendly, accessible, and novel approach for the detection, counting, and grading of tomatoes found on a farm. An Augmented Reality (AR) based mobile application is developed to obtain the images efficiently from a tomato farm in the pre-harvest stage subjected to open situations. The proposed approach uses Faster RCNN, a convolutional neural network model for detection of tomatoes from the input image on a large scale. The proposed model is trained and tested using 2083 images. The results are then analyzed for the overall performance of detection, segmentation, and classification of tomatoes. The results have examined the efficiency of the proposed mobile application and demonstrate the robustness it exhibits for the detection, grading and yield prediction of Tomatoes.

关键词： tomato detection tomato grading tomato yield prediction augmented reality deep learning

来源：评论

学校读者我要写书评

暂无评论

Assessing Secure Cloud Information Sharing Through Authentication and Encoded Indexing 8

Assessing Secure Cloud Information Sharing Through Authentic...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Pandiaraja, P. Karthik, K. Rajesh Kanna, P. Ushapriya, C. Mahesh, P.C.Senthil Muthumanickam, K. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai600 062 India M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur Tamilnadu Thalavapalayam639113 India Bannari Amman Institute of Technology Department of Computer Science and Engineering Tamilnadu Erode638401 India St. Martin's Engineering College Department of Ai & Ml Telangana Secunderabad500100 India Excel Engineering College Department of Computer Science and Engineering Tamilnadu Komarapalayam637303 India Kongunadu College of Engineering and Technology Department of Information Technology Tamil Nadu Trichy621215 India

ISBN: (纸本)9798350376425

The high usage of storage in cloud, ensuring the privacy and security of information stored in the cloud has come up with a difficult concern. One approach to address this issue is the use of techniques which are encrypted, where data is already encrypted being uploaded to the storage of cloud. However, traditional encryption methods hinder the ability to find and retrieve particular information from the secured information, as the information needs to be decrypted first. This limitation hampers the usability and efficiency of storage of cloud systems. To overcome the challenge, this research says a novel approach for keyword search on secured information in storage of cloud using an AES approach. The algorithm of AES is a maximum adopted symmetric encryption method familiar for efficiency and robustness. By leveraging the AES encryption approach, the solution assures the confidentiality of information stored while enabling efficient keyword-based search operations without the need for decryption. The proposed approach utilizes a combination of cryptographic techniques such as AES encryption and index structures to access efficient information findings on the secured information. A secure index is created during encryption process that enables for potent retrieval of encrypted data related to specific keywords. The encrypted data remains confidential, as only authorized users possess the necessary decryption keys to retrieve the plaintext information. During data outsourcing, data owner can set the access permission based on their user identity. Users should have specific identity with decryption key for accessing data from cloud. Here data manager can also provide particular period for accessing information from cloud. The results demonstrate that the keyword findings on secured information in storage of using the AES approach achieve a balance between data privacy and search functionality. The solution offers an effective means to securely store and retrieve data

关键词： Cloud storage

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：