检索结果-内蒙古大学图书馆

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

作者： Dey, Amritangshu Aishwaryasri, J. Jai Surya, R. Jayanthi, M.G. Kannadaguli, Prashanth Cambridge Institute of Technology Department of Computer Science Engineering Bengaluru India Dhaarini Academy of Technical Education Bengaluru India

ISBN: (纸本)9798350313413

Platforms for social media are dynamic tools that help ideas spread and develop quickly. This study introduces a novel way of locating popular Kannada-language subjects on social networking sites. This study also involves data preprocessing, feature extraction, and data visualization approaches to reveal underlying patterns and insights using a sizable dataset made up of Kannada text, tweets, hashtags, and news headlines. This method efficiently incorporates both sophisticated Machine Learning models, such as N-grams and word tokenization, and Deep Learning models, including sentence transformers and U-map embeddings. The examination of coherence and silhouette scores is used to validate the models. The main goal of this research is to offer an in-depth analysis of issues that regularly come up in Kannada debates on social media. This enables organizations, researchers, and content producers to make well-informed decisions, comprehend user opinion more thoroughly, and keep up with rapidly changing technological developments. In essence, this study helps provide a thorough understanding of the constantly changing digital ecosystem. © 2023 IEEE.

关键词： Bidirectional Encoder Representations from Transformers (BERT) Kannada language Latent Dirichlet Allocation (LDA) Natural Language Processing (NLP) social media Topic modelling Transformer trend

来源：评论

学校读者我要写书评

暂无评论

A Secure Authentication Model with Optimized Key Generation in IoT-Fog-Cloud Computing

A Secure Authentication Model with Optimized Key Generation ...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Babitha, M.N. Siddappa, M. Siddharetha Instiute of Technology Tumakuru Sri Siddhartha Academy of Higher Education Department of Computer Science and Engineering Tumakuru India

ISBN: (纸本)9798350315455

With a rise in cloud computing, numerous organizations and businesses units utilized the cloud servers to expand their operations, which leads to lower equipment cost and effective resources utilization. The fog system is operated among the cloud-based IoT, that offered a hierarchy of computing resources for collecting, aggregating, and processing the data from IoT devices. Moreover, the private key is generated to encrypt the data for secure authentication of IoT-Fog-Cloud computing. In this work, hybrid optimization enabled optimal key is generated for data protection. The entities considered for secure authentication-based data protection includes user, fog devices and cloud server. Moreover, the steps like initialization, registration, key generation, authentication and verification as well as data protection is carried out. Furthermore, the secure authentication is done using the security operations like EXOR, hashing, encryption and decryption. In private key generation the proposed Chronological Jelly Fish optimization is utilized. © 2023 IEEE.

关键词： Authentication cloud computing Internet of things Jelly fish optimization key generation

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Deep Neural Network Technique for Prediction of Morality Risk in Patients with Corona Virus Disease 2

Fuzzy Deep Neural Network Technique for Prediction of Morali...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Balakrishnan, D. Mariappan, Umasree Reddy, S Manideep Kumar Aravindan, T.M. Yaswanth, Mupparaju Naidu, Pidikiti Narasimha Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnakoil626126 India Sri Vidya College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Virudhunagar626005 India

ISBN: (纸本)9798350308846

Predicting risks in patients with Corona Virus Disease 19 (COVID-19) involves assessing the likelihood and severity of various outcomes, such as hospitalization, ICU admission, disease progression, or mortality. Machine learning models, including deep neural networks, can be used for this task by leveraging patient data to make predictions. In contrast to using deep learning techniques for COVID-19 disease detection through image analysis, an approach was proposed that combined feature selection, instance clustering and Deep Neural Network (DNN) to forecast the threat of morality in COVID-19 patients. However, DNN struggles with handling uncertain and imprecise data. In addition to this, DNN is sensitive to variations and outliers in the input data. In this paper, Fuzzy DNN (FDNN) is introduced to handle the uncertainty, data variation and outliers in input data for better prediction of risks in patients with COVID-19. FDNN is a deep neural network that combines fuzzy and neural representations to derive information. The knowledge obtained from both views is integrated to create the final data representation for prediction of risks in patients with COID-19. The findings indicate that the suggested approach using FDNN yields superior accuracy, precision, and recall in predicting COVID19 patients. © 2023 IEEE.

关键词： Corona virus disease deep learning deep neural network fuzzy deep neural network

来源：评论

学校读者我要写书评

暂无评论

Methods for Human Identity Verification in Smart Unmanned Supermarkets Based on computer Vision 9

Methods for Human Identity Verification in Smart Unmanned Su...

引用

9th IEEE International Conference on Smart Cloud, SmartCloud 2024

作者： Liu, Lizheng Cai, Zhebiao Xu, Jianqiang Fudan University Academy for Engineering and Technology Shanghai China Fudan University School of Computer Science and Technology Shanghai China Shanghai Fine Electronic.LTD Shanghai China

ISBN: (纸本)9798350389500

Smart unmanned supermarkets have been emerging in the past years and significantly affected conventional shopping styles. Customer identification is an important step in picking up goods in smart unmanned supermarkets. However, in the actual application scenario, the camera can only capture part of the human body information, which is a challenge to identify individual consumers. This paper introduces an approach that integrates facial recognition with body re-identification (REID) algorithms to continuously update human feature information. The object detection method based on YOLOV4 is adopted to detect the human body in the unmanned supermarket. A full-scale network OSNet is used for human feature extraction. Finally, the cosine similarity of the extracted feature vector is calculated to obtain the similarity of human features. The experimental results show that the final similarity exceeds the set threshold value of 0.6, which can meet the needs of identity recognition for unmanned supermarkets. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Automated Diabetic Retinopathy Prediction Using a Deep Learning Based Modified DenseNet 2

Automated Diabetic Retinopathy Prediction Using a Deep Learn...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Balakrishnan, D. Mariappan, Umasree Reddy, Vajrala Pavan Sainath Chaitanya, Darimadugu Venkata Manohar, Nalluri Reddy, Lella Srinivasa Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnakoil626126 India Sri Vidya College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Virudhunagar626005 India

ISBN: (纸本)9798350308846

Diabetic Retinopathy (DR) is a form of diabetes caused by damage to the retinal blood vessels. Early identification and treatment of this condition are facilitated through retinal screening. DR progresses through five phases: usual, malignant, acute, moderate and slight. To enable early detection and intervention, computer-aided diagnostic methods are essential. Numerous deep learning-based automated approaches have demonstrated their effectiveness in accurately grading DR. In this paper, a deep leaning technique called modified Densenet-169 is proposed for early detection of DR. Initially, the retinal images are pre-processed using Gabor filter to enhance the visibility of blood vessels for easy detection of DR. Then the size of the dataset is increased by using image data generator. Finally, the images are processed in modified Densenet-169 which classifies retinal images as absence of DR, light DR, beginner DR, serious DR, and progressive DR. The performance of DenseNet is enhanced by including four pairs of dense blocks and transition layers. Dense block in DenseNet combines feature maps by concatenation, while the transition layer reduces the dimensions via a composite of average pooling, 1x1 convolution, and batch normalization. The empirical observations showcase that the modified Densenet169, as proposed, achieves superior levels of accuracy, precision, and recall in DR detection than cutting-edge methods. © 2023 IEEE.

关键词： deep learning Diabetic retinopathy gabor filter image data generator modified densenet-169

来源：评论

学校读者我要写书评

暂无评论

Dynamic Changing Trustability Based Secured Protocol For Collaborative Data Transmission In Mobile Adhoc Network 3

Dynamic Changing Trustability Based Secured Protocol For Col...

引用

3rd IEEE Asian Conference on Innovation in technology, ASIANCON 2023

作者： Mariappan, Umasree Balakrishnan, D. Devi, G. Durga Alagusundar, Nanditha Aravindan, T.M. Nalatharaj, R.Jebi Sri Vidya College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Virudhunagar626001 India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnankoil626126 India

ISBN: (纸本)9798350302288

Secured data transmission in mobile adhoc network is an more difficult where there will not be any decentralized environment to monitor the packet transmission progress. There are various methods has been introduced earlier for ensuring the secured data transmission. However those research methodologies tends to have more demerits such as reduced data delivery rate, increased delay and so on. These problems are focused and resolved in the proposed research methodology by introducing the method namely Dynamic Changing Trustability based Secured MANET Protocol (DCT-SMANET-P). In this method, trustable nodes in the network environment will be find out first, through which data transmission will be carried out. Once trust values are evaluated, direct route path between the network nodes will be estimated based on which most trustable nodes will be chooses and the network carrier changes will be calculated. After trust estimation, routing will be carried out by choosing the most suitable route path through which data transmission will be carried out. The overall simulation of the research work is carried out in the NS3 simulation environment from which it is proved that the proposed methodology attains better outcome than the existing methodologies. © 2023 IEEE.

关键词： Data communication systems

来源：评论

学校读者我要写书评

暂无评论

Drowsiness Detection for Drivers using Hybrid T-Distributed Stochastic Neighbor Embedding with Convolutional Neural Network 2

Drowsiness Detection for Drivers using Hybrid T-Distributed ...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Balakrishnan, D. Mariappan, Umasree Nikhitha, Balabhadra Akshitha, Bokkisam Visali, Bedamsetty Snehalatha, Bandikattu Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnankoil626126 India Sri Vidya College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Virudhunagar626005 India

ISBN: (纸本)9798350308846

Drowsiness Detection (DD) is the procedure of identifying signs of drowsiness in individuals, especially in critical situations like driving, heavy machinery operation, or aircraft piloting. Hybrid Bi-directional Long Short Term Memory with Convolutional Neural Network (HBLSTM-CNN) was proposed for driver's DD. At first, an eye dataset was gathered and subsequently subjected to pre-processing using a shape predictor. The pre-processed images are initially analyzed using a BiLSTM to identify the most prominent characteristics, which are subsequently subjected to additional processing in a CNN to serve the purpose of DD. Nonetheless, as the data's dimensionality grows, BiLSTM demands more computational resources, including memory and processing power. So in this paper, Hybrid t-distributed Stochastic Neighbor Embedding with CNN (Ht-SNE-CNN) is introduced for driver's DD. In Ht-SNE-CNN, t-SNE is utilized for reducing dimensionality because of its inherent simplicity, obviating the requirement to train a sophisticated model. It directly computes a lower-dimensional depiction of the data while emphasizing the preservation of local similarities. This inherent simplicity frequently leads to faster and more direct utilization, particularly when handling high-dimensional data. The reduced data are given as input to CNN for driver's DD. The experimental findings demonstrate that the suggested HtSNE-CNN outperforms HBLSTM-CNN with regard to exactness, precision, and recall for detecting driver drowsiness. © 2023 IEEE.

关键词： bi-directional long short term memory convolutional neural network dimensionality reduction Drowsiness detection t-distributed stochastic neighbor embedding

来源：评论

学校读者我要写书评

暂无评论

Identity – Attribute Inference in Online Social Network(s) Using Bio-Inspired Algorithms and Machine Learning Approaches

引用

Journal of Mobile Multimedia 2023年第3期19卷 645-678页

作者： Shetty, Nisha P. Muniyal, Balachandra Teja, Daita Ravi Maben, Leander Melroy Vinil, Tummala Srinag Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal 567104 India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal 567104 India

Twitter is one of the most popular social networking sites today, and it has become a critical tool for gathering data from numerous individuals throughout the world. The platform hosts a variety of debates spanning from current events and news to entertainment, advertising, and technology. In contrast to earlier approaches, the proposed work employs the concept of both direct (via tweets) and indirect stance detection (via homophily elements) to infer sensitive attributes. Along with attribute-based inference, the proposed work also matches user profiles across cross platforms via user-generated posts. Unlike prior efforts, usernames are not included in the feature set here since they are a bit of a giveaway. Bio-inspired algorithms are used along with ensemble methods to extract the best set of features. © 2023 River Publishers.

关键词： attribute inference bio-inspired algorithms ensemble homophily Identity inference

来源：评论

学校读者我要写书评

暂无评论

Data Deduplication using Machine Learning 15

Data Deduplication using Machine Learning

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Revanth, Narasimhula Varun, Ravuri Harshitha, Ebbili Angelina, J. Jane Rubel Subhashini, S.J. Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamil Nadu Virudhnagar India Department of IT SRM Madurai College for Engineering and Technology Tamil Nadu Madurai India

ISBN: (纸本)9798331300579

Reducing data in storage systems is becoming more crucial as a practical way to cut down on data Center management expenses. Current post-deduplication delta-compression techniques combine delta compression with lossless compression and conventional data deduplication to optimize data reduction efficiency. Regretfully,we observe that because of their poor accuracy in identifying similar data blocks, current techniques achieve noticeably lower data-reduction ratios than the optimal. Data deduplication is a computing technique that removes duplicate copies of data that repeats. A similar and almost interchangeable term is single-instance data storage. This method will be used to reduce bytes that need to be sent during network data transfers same as to increase storage utilization. During the de-duplication process, distinct data segments, also known as byte patterns, are found and saved after analysis. Further chunks are compare with the stored copy as the analysis progresses, and if a match is found, the redundant chunk is substituted with a brief reference pointing to the stored chunk. Reduced data storage or transfer requirements result from the possibility same as byte pattern occurring hundreds, thousands, or even more times (match frequency depends on chunk size). Comparing data segments to find duplicates is how most recognized methods for data deduplication is implemented. © Grenze Scientific Society, 2024.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Identifying malicious traffic under concept drift based on intraclass consistency enhanced variational autoencoder

引用

science China(Information sciences) 2024年第8期67卷 238-252页

作者： Xiang LUO Chang LIU Gaopeng GOU Gang XIONG Zhen LI Binxing FANG Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Technology Harbin Institute of Technology (Shenzhen)

Accurate identification of malicious traffic is crucial for implementing effective defense countermeasures and has led to extensive research efforts. However, the continuously evolving techniques employed by adversaries have introduced the issues of concept drift, which significantly affects the performance of existing methods. To tackle this challenge, some researchers have focused on improving the separability of malicious traffic representation and designing drift detectors to reduce the number of false ***, these methods often overlook the importance of enhancing the generalization and intraclass consistency in the representation. Additionally, the detectors are not sufficiently sensitive to the variations among different malicious traffic classes, which results in poor performance and limited robustness. In this paper, we propose intraclass consistency enhanced variational autoencoder with Class-Perception detector(ICE-CP) to identify malicious traffic under concept drift. It comprises two key modules during training:intraclass consistency enhanced(ICE) representation learning and Class-Perception(CP) detector construction. In the first module, we employ a variational autoencoder(VAE) in conjunction with Kullback-Leibler(KL)-divergence and cross-entropy loss to model the distribution of each input malicious traffic flow. This approach simultaneously enhances the generalization, interclass consistency, and intraclass differences in the learned representation. Consequently, we obtain a compact representation and a trained classifier for nondrifting malicious traffic. In the second module, we design the CP detector, which generates a centroid and threshold for each malicious traffic class separately based on the learned representation, depicting the boundaries between drifting and non-drifting malicious traffic. During testing, we utilize the trained classifier to predict malicious traffic classes for the testing samples. Then, we use the CP det

关键词： concept drift malicious traffic identification variational autoencoder intrusion detection cyberspace security

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：