检索结果-内蒙古大学图书馆

3rd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2024

作者： Rohith, R. Senthilnayaki, B. Joshua Dayalan, M. Anna University College Of Engineering Department of Information Science and Technology India Anna University College Of Engineering Department of Computer Science and Engineering India

ISBN: (数字)9798350391565

ISBN: (纸本)9798350391565

Heart Disease is still an epidemic global health concern, so trustworthy prediction models are vital for risk assessment and early detection. In this research, we propose a comprehensive predictive framework leveraging ensemble learning techniques alongside traditional Machine Learning (ML) models to increase forecasting of cardio disease accuracy. Utilizing a dataset sourced from Cardiovascular-Disease-Dataset, demographic, clinical, and lifestyle factors were incorporated as features. The performance of Naive Bayes (NB), AdaBoost, Support Vector Classifier (SVC) and Logistic Regression (LR) both individually and within ensemble frameworks, was evaluated using accuracy of 98% and AUROC (Area-Under the Receiver Operating Characteristic Curve) of 99.845% as a primary metric. Our results demonstrate how effective ensemble learning strategies are in obtaining higher accuracy, precision-recall and along with AUROC curve for heart disease prediction compared to individual classifiers. This study underscores the importance of ensemble methods in improving predictive performance and contributing to enhanced clinical decision-making in cardiovascular health management. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Hybrid RR Algorithm for Anomaly Detection in Streaming Data

引用

computer Systems science & engineering 2023年第6期45卷 2299-2312页

作者： L.Amudha R.PushpaLakshmi Department of Computer Science and Engineering K.Ramakrishnan College of EngineeringTrichyTamilnadu-621112India Department of Information Technology PSNA College of Engineering and TechnologyDindigulTamilnadu-624622India

Automated live video stream analytics has been extensively researched in recent *** of the traditional methods for video anomaly detection is supervised and use a single classifier to identify an anomaly in a *** propose a 3-stage ensemble-based unsupervised deep reinforcement algorithm with an underlying Long Short Term Memory(LSTM)based Recurrent Neural Network(RNN).In the first stage,an ensemble of LSTM-RNNs are deployed to generate the anomaly *** second stage uses the least square method for optimal anomaly score *** third stage adopts award-based reinforcement learning to update the *** proposed Hybrid Ensemble RR Model was tested on standard pedestrian datasets UCSDPed1,*** data set has 70 videos in UCSD Ped1 and 28 videos in UCSD Ped2 with a total of 18560 *** a real-time stream has strict memory constraints and storage issues,a simple computing machine does not suffice in performing analytics with stream *** the proposed research is designed to work on a GPU(Graphics Processing Unit),TPU(Tensor Processing Unit)supported *** shown in the experimental results section,recorded observations on framelevel EER(Equal Error Rate)and AUC(Area Under Curve)showed a 9%reduction in EER in UCSD Ped1,a 13%reduction in ERR in UCSD Ped2 and a 4%improvement in accuracy in both datasets.

关键词： Anomaly detection deep learning ensemble real-time surveillance video

来源：评论

学校读者我要写书评

暂无评论

Ranking of Documents Through Smart Crawler 3rd

Ranking of Documents Through Smart Crawler

引用

3rd International Semantic Intelligence Conference, ISIC 2023

作者： Dange, Amol S. Swamy, B. Manjunath Shinde, Ashwini B. Department of Computer Science & Engineering Annasaheb Dange College of Engineering & Technology Maharashtra Ashta India Department of Computer Science & Engineering Don Bosco Institute of Technology Bangalore India

ISBN: (纸本)9789819773558

With the exponential boom in information storage on the internet these days, search engines like Google are of extreme significance. The critical issue of a search engine, ranking models are techniques utilized in engines like Google to find relevant pages and rank them in lowering order of relevance. The offline gathering of those papers is important for offering the consumer with more accurate and pertinent findings. Earlier when an end-user issues a question, crawling is the system of retrieving documents from the web. With the internet’s ongoing expansion, the quantity of files that need to be crawled has grown surprisingly. It's crucial to wisely rank the files that want to be crawled in each iteration for any academic or mid-degree organization because the resources for non-stop crawling are constant. Algorithms are created to deal with the crawling pipeline already in the area while bringing the blessings of ranking. These algorithms ought to be quick and effective to save you from turning into a pipeline bottleneck. The proposed method uses the Hamming distance algorithm application. Also, this method incorporates parallel processing by using Kafka in between subtasks. Primarily, based on the Hamming Distance algorithm software, the quest engine is designed for, an effective smart crawler is created that ranks the page that needs to be downloaded in each new release. Evaluating with different present methods, the implemented Hamming Distance technique achieves an excessive accuracy of 99.8%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

A Concise and Varied Visual Features-Based Image Captioning Model with Visual Selection

引用

computers, Materials & Continua 2024年第11期81卷 2873-2894页

作者： Alaa Thobhani Beiji Zou Xiaoyan Kui Amr Abdussalam Muhammad Asim Naveed Ahmed Mohammed Ali Alshara School of Computer Science and Engineering Central South UniversityChangsha410083China Electronic Engineering and Information Science Department University of Science and Technology of ChinaHefei230026China EIAS Data Science Lab College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia College of Computer and Information Sciences Prince Sultan UniversityRiyadh11586Saudi Arabia College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic UniversityRiyadh11432Saudi Arabia

Image captioning has gained increasing attention in recent *** characteristics found in input images play a crucial role in generating high-quality *** studies have used visual attention mechanisms to dynamically focus on localized regions of the input image,improving the effectiveness of identifying relevant image regions at each step of caption ***,providing image captioning models with the capability of selecting the most relevant visual features from the input image and attending to them can significantly improve the utilization of these ***,this leads to enhanced captioning network *** light of this,we present an image captioning framework that efficiently exploits the extracted representations of the *** framework comprises three key components:the Visual Feature Detector module(VFD),the Visual Feature Visual Attention module(VFVA),and the language *** VFD module is responsible for detecting a subset of the most pertinent features from the local visual features,creating an updated visual features ***,the VFVA directs its attention to the visual features matrix generated by the VFD,resulting in an updated context vector employed by the language model to generate an informative *** the VFD and VFVA modules introduces an additional layer of processing for the visual features,thereby contributing to enhancing the image captioning model’s *** the MS-COCO dataset,our experiments show that the proposed framework competes well with state-of-the-art methods,effectively leveraging visual representations to improve *** implementation code can be found here:https://***/althobhani/VFDICM(accessed on 30 July 2024).

关键词： Visual attention image captioning visual feature detector visual feature visual attention

来源：评论

学校读者我要写书评

暂无评论

Towards Precision Dementia Detection: Integrating ML and Clinical Data 2

Towards Precision Dementia Detection: Integrating ML and Cli...

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Kandula, Niravange Chakravarty, Sujata Kandula, Aksha Mohapatra, Sunil Kumar Centurion University of Technology & Management Computer Science & Engineering Vizianagaram India Centurion University of Technology & Management Computer Science & Engineering Bhubaneswar India Andhra University College of Engineering Computer Science & Engineering Andhra Pradesh Visakhapatnam India

ISBN: (纸本)9798350370188

The dominant pathology theory holds that dementia results from amyloid buildup, followed by tau protein aggregation and neurodegeneration. Current anti-amyloid and anti-tau therapies, however, show varied therapeutic success. Atypical Alzheimer's disease has radiologic and clinical symptoms with other medical conditions, making accurate diagnosis even more challenging. Our approach employs machine learning algorithms to analyze a dataset that includes clinical evaluations, neuropsychological assessment scores, and biomarker measures. The information was gathered from a broad group of people with varying cognitive states, including those in the preclinical and moderate cognitive impairment (MCI) phases as well as AD patients. This study has important implications for clinical practice, permitting prompt therapies, and advancing our understanding of the progression of Alzheimer's disease. When integrated with Boruta as a feature selector, random forest outperformed upon fine-tuning on both datasets. © 2024 IEEE.

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Recognition using Convolutional Neural Networks YOLOv3 Algorithm

Traffic Sign Recognition using Convolutional Neural Networks...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Gnanabaskaran, A. Pranav Ram, K.S. Vaishnavi, N. Shabari Prasannaa, D. K S Rangasamy College of Technology Faculty of Computer Science and Engineering Department of Computer Science and Engineering Tiruchengode India K S Rangasamy College of Technology Computer Science and Engineering Department of Computer Science and Engineering Tiruchengode India

ISBN: (纸本)9798350300857

Nowadays, traffic sign recognition is disrupted through various external factors such as chromatic aberration, geographical separation, and brightness of lights. This eventually poses possible safety hazards during navigation in real life. To overcome this issue, a deeplearning based method is proposed in this research using YOLOv3 with DenseNet as the backbone design. This approach uses attention mechanism to accelerate the feature extraction process by minimizing the overhead due to high computations to optimize the latency problem. Secondly, it incorporates location-specific hierarchical network to increase the traffic sign detection performance in challenging circumstances such as magnitude and illumination variations while maintaining adaptability and flexibility. In addition to this Cross Stage Partial Network is fused with DenseNet to enhance the recognition accuracy and effectiveness of the proposed system. The experimental findings on the Chinese Traffic sign dataset, CCTSDB dataset, showed that the YOLOv3-DenseNet model exhibited significant detection efficiency of 97.6% than the other deep learning models considered for performance comparison. It is observed that the proposed model is capable enough to detect the traffic signs in complicated scenarios as well as in places where the traffic signs are placed in smaller dimensions. © 2023 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Implementation of Secure and Verifiable Access Control Procedures using the NTRU Cryptosystem to Store Big Data in the Cloud Environment

引用

Recent Patents on engineering 2025年第2期19卷 57-70页

作者： Babu B, Ravindra Saxena, Swati Widjaja, Gunawan Vinodha D, Vedha Omarov, Batyrkhan Ramaiah, Gurumurthy B. Vats, Prashant Adama Ethiopia Department of Computer Science KCG College of Technology Chennai India Universitas Krisnadwipayana Jawa Barat 13077 Indonesia Department of Electronics and Communication Engineering JCT College Of Engineering and Technology Pichanur Coimbatore India International University of Tourism and Hospitality Turkistan Kazakhstan Technical and Vocational Training Institute Addis Ababa Ethiopia Department of Computer Science and Engineering Faculty of Engineering and Technology SGT University Haryana Gurugram India

Background: Due to their complexity and size, deploying ciphertexts for clouds is considered the most useful approach to accessing large data stores. Methods: However, access to a user's access legitimacy and improving a decrypted text on the cloud depending on an improved access policy (AP) specified by the data owner are the key challenges for making large data storage realistic and effective in clouds. The traditional ways either totally remove the problem of AP development or offer renewal to arbiter power, but in real-time, enhancing the AP is essential to maximising security and handling agility. Results: In this patent paper, a safe and verifiable access control program characterised by the NTRU cryptographic system for large storage of data in the clouds is proposed. Primarily, an improved NTRU decryption protocol to deal with the decryption failures of the prime NTRU is established, and in addition, the program is analysed for its security strength and computational performance. When a new AP is specified by the data owner, the cloud server allows the program to improve ciphertext and allows the owner to verify the upgrade to oppose the cloud's fraudulent behaviour. Conclusion: It enables (i) checking the user's legitimacy to access the data owner and qualified users, and (ii) allowing the user to verify the data provided by other users for the recovery of the right user. Strong analysis can prevent and block delinquency from various attacks, namely the collusion attack that could potentially target fraud users. © 2025 Bentham science Publishers.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

GSM based LPG Leakage Detection and Simulation System 2

GSM based LPG Leakage Detection and Simulation System

引用

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Ramanan, K. Vashali, S. Nanthini, S. Thaqfeen, M. Hifaya Sivaraja, P.M. Maheswari, G. Uma Npr College of Engineering and Technology Department of Computer Science Engineering TamilNadu India Amrita College of Engineering Department of Computer Science Engineering TamilNadu India Rmk College of Engineering and Technology Department of Computer Science Engineering TamilNadu Chennai India

ISBN: (纸本)9798350347579

In a time when LPG is increasingly used as a fuel source for factories, houses, and cars, any accidental releases would have devastating consequences. Detectors for LPG leaks should be placed in potentially hazardous places as a precaution. Therefore, the purpose of this study is to develop an LPG leak detection and reaction system using a microcontroller. The MQ-6 gas sensor is used to detect leaks, and the user is notified by GSM-based text message and an audible alarm. LPG supply was cut off to reduce waste and avoid mishaps, which was a primary function of the system. This was accomplished by consulting datasheets while deciding which components to include in the circuit design, and by running simulations of the circuit in Proteus to check its viability. When the amount of LPG in the air reaches a certain level, the system sends a text message to a user-specified cell phone number stored in the microcontroller and concurrently triggers the warning buzzer and displays the data on an LCD. The LPG supply may be cut off by sending a signal to the solenoid valve. This setup notifies you of a gas leak and immediately cuts off the gas supply, so you don't waste any fuel and don't risk any mishaps. LPG vendors and consumers alike will benefit greatly from this approach. © 2023 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neural Network-Based Improved Fabric Defect Detection Scheme 12th

Adaptive Neural Network-Based Improved Fabric Defect Detecti...

引用

12th International Conference on Recent Trends in Computing, ICRTC 2024

作者： Prabha, P. Anantha Abirami, S. Varshini, N. Amirtha Garishma, K. Priya, M. Deva Karthick, S. Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Tamil Nadu Coimbatore India Department of Computer Science and Engineering Sri Krishna College of Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering Karpagam College of Engineering Tamil Nadu Coimbatore India Department of Computer Science and Engineering Delhi - NCR Campus SRM Institute of Science and Technology Uttar Pradesh Ghaziabad India

ISBN: (纸本)9789819789450

Efficient detection of defects in fabric plays a dominant role in automating quality control. It significantly enhances efficiency as well as accuracy of quality assurance in textile manufacturing. Skilled humans who physically examine defective designs in numerous sectors use traditional defect detection techniques. The main drawbacks of manual methods include deficiency of concentration, inaccuracy, weariness and increased time consumption. computer Vision (CV) and Digital Image Processing (DIP) techniques may be efficient in overcoming these shortcomings. The proposed approach involves data acquisition to record images which are subsequently pre-processed using histogram equalization to improve the defective area. A distinctive Neural Network (NN) is used for defect detection. This method improves precision and efficiency in identifying defects. The proposed method is built using Adaptive NNs (ANNs) along with Radial Basis Functions (RBFs) and is aimed at revolutionary identification of fabric flaws. The networks are built using attributes derived from images segmented using Expectation Maximization (EM) depending on target’s region attributes. As a result, the type of defects is classified based on the extracted features, thus yielding increased detection accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis of using Deep Learning and Machine Learning technologies for intrusion detection for effective network traffic analysis 7

A comparative analysis of using Deep Learning and Machine Le...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Divya, S.B. Mary, S. Prince Department of Computer Science and Engineering Sathyabhama Institute of Science & Technology Chennai India Mangalam College of Engineering Department of Computer Applications India

ISBN: (纸本)9798350372816

The broad utilization of interconnectivity and interoperability of processing frameworks have turned into an irreplaceable need to improve our everyday activities. All the while, it opens a way to exploitable weaknesses that work out positively past human control capacity. The weaknesses consider network protection instruments fundamental to accepting correspondence trade. Secure correspondence requires safety efforts to battle the dangers and necessities headways to safety efforts that counter advancing security dangers. So, emerging technologies like Deep Learning/ Machine Learning (DL/ML) come in handy for integration and better prediction. So, in this paper, we depict various deep learning/ML strategies used in detecting the imbalance in network traffic. The document also includes research that has been proposed on the topic of intrusion detection in network traffic over the previous four years (2020-2024) by a variety of research specialists. The main achievements of the security measures are recognized in this review together with their quantitative and qualitative success indicators. Additionally, as a guide for upcoming discoveries, this research study examines the major discoveries and the rationale for the lessons discovered. © 2024 IEEE.

关键词： Network intrusion

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：