检索结果-内蒙古大学图书馆

2nd International Conference on Smart Technologies, Communication and Robotics, STCR 2022

作者： Viswapriya, S.E. Rajeswari, D. SRM Institute of Science and Technology School of Computing College of Engineering and Technology Department of Data Science and Business System Tamilnadu India

ISBN: (纸本)9781665460477

There is an enormous increase in number of diseases worldwide. The non-communicable diseases such as cardio vascular disease will leads to death. The second major reason of death in people worldwide occurs due to stroke. It affects any portion of brain due to interruption or reduction of Blood supply. The brain damage can be reduced if required actions taken earlier. So there is necessary requirement to build stroke predictive models. The combined techniques of Machine Learning (ML) and Deep Learning (DL) techniques play the vital role in Disease Prediction. There are many researches has been done for stroke prediction using various ML Algorithms. In order to improve accuracy, the proposed model will work on the hybrid ANNRF (Artificial Neural Network-Random Forest). The proposed method can be reached 94% in classification accuracy. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Detection of Pancreatic Cancer Cells at Early Stage and Recommend the Treatment Process 6

Detection of Pancreatic Cancer Cells at Early Stage and Reco...

引用

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

作者： Margret Sharmila, F. Shree Harini, R. Vityarubbasiri, M. Gopi Krishna, S. Sri Krishna College of Engineering and Technology Department of Computer Science and Business System Coimbatore641008 India

ISBN: (纸本)9798350394702

Early identification and diagnosis of cancerous cells will focus on the symptomatic patients, to give the best way of successful treatment. When the detection of cancer is delayed, then there is a lower chance of survival, high problems with treatment and higher cost estimates. Considering Pancreas Cancer growth, a type of cancer that is difficult to identify because there are less or no symptoms found at the early stage. So, we introduce Artificial Intelligence (AI) technology to identify pancreatic cancer cells. This is the first insight that is provided to detect cancerous cells at the early stage. With the use of technologies, anything is possible, so we use the process of medical imaging analysis, data processing and Machine Learning (ML) for the recognition. data is collected through MRI and CT scan reports, biomarkers tests, liquid biopsies, endoscopic techniques, early symptom monitoring, and genetic testing which is then categorized into train and test sets. Every training data set is analyzed to provide a standard image to extract the features with the use of OpenCV. Building an AI model with the use of the Convolutional Neural Network (CNN) algorithm with an efficient set of filters. Training the model with the training data set helps to improve the accuracy of predicting results. When it is ready, the testing data set is used to check the accuracy of predictions. Finally, by assessing the model based on the performance metrics from both training and testing datasets, accuracy is achieved. After achieving a certain level of accuracy, and leveraging ML algorithms such as Hybrid models, the system can provide treatment recommendations consistent with a separate training dataset. This training dataset comprises predicted treatments corresponding to the achieved accuracy. After, the system is prepared for deployment. The envisioned process can track the patient's status for future use. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Application of Bayes Rule for Precise Analysis of Class-Imbalanced Stroke data

Application of Bayes Rule for Precise Analysis of Class-Imba...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical systems, ICSES 2023

ISBN: (纸本)9798350319200

The interpretability of stroke risk prediction is still lagging and it can be solved by using deep analysisofdata with the application of the Bayes rule. The prediction model has to be produced with accuracy, clarity, and comprehensibility without ambiguity, especially in machine learning and data analytics. The class imbalance problem is a common issue affecting the raw data, which means the imbalanced categorization of outcome feature value. In many fields, such as fraud detection, network intrusion detection, and medical diagnostics, this class imbalance issue is present where negative class samples outnumber positive class samples. If some datasets have class imbalance and imperfect issues, there will be no proper classification pattern. There are many resampling methods to address this class imbalance problem. However, these resampling methods can make an even distribution of classes by generating or omitting some samples, but theycannot handle imperfect data. The probabilistic analysis can lead to the identification of issues that exist in the dataset and provide direction to medical experts on dealing with the condition to avoid *** strength of applying the Bayes rule will provide a meaningful interpretation of stroke data. This paper investigates the Baye rule's significance in stroke data analysis. © 2023 IEEE.

关键词： Bayes rule Class imbalance probabilistic analysis Resampling Stroke data

来源：评论

学校读者我要写书评

暂无评论

Message Verification Protocol Based on Bilinear Pairings and Elliptic Curves for Enhanced Security in Vehicular Ad Hoc Networks

引用

Computers, Materials & Continua 2024年第10期81卷 1029-1057页

作者： Vincent Omollo Nyangaresi Arkan A.Ghaib Hend Muslim Jasim Zaid Ameen Abduljabbar Junchao Ma Mustafa A.Al Sibahee Abdulla J.Y.Aldarwish Ali Hasan Ali Husam A.Neamah Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo40601Kenya Department of Applied Electronics Saveetha School of EngineeringSIMATSChennaiTamilnadu602105India Information Technology Department Management Technical CollegeSouthern Technical UniversityBasrah61004Iraq Department of Computer Science College of Education for Pure SciencesUniversity of BasrahBasrah61004Iraq College of Big Data and Internet Shenzhen Technology UniversityShenzhen518118China Huazhong University of Science and Technology Shenzhen InstituteShenzhen518000China National Engineering Laboratory for Big Data System Computing Technology Shenzhen UniversityShenzhen518060China Computer Technology Engineering Department Iraq University CollegeBasrah61004Iraq Department of Mathematics College of Education for Pure SciencesUniversity of BasrahBasrah61004Iraq Institute of Mathematics University of DebrecenDebrecenH-4002Hungary Department of Electrical Engineering and Mechatronics Faculty of EngineeringUniversity of DebrecenDebrecen4028Hungary

Vehicular ad hoc networks(VANETs)provide intelligent navigation and efficient route management,resulting in time savings and cost reductions in the transportation ***,the exchange of beacons and messages over public channels among vehicles and roadside units renders these networks vulnerable to numerous attacks and privacy *** address these challenges,several privacy and security preservation protocols based on blockchain and public key cryptography have been proposed ***,most of these schemes are limited by a long execution time and massive communication costs,which make them inefficient for on-board units(OBUs).Additionally,some of them are still susceptible to many *** such,this study presents a novel protocol based on the fusion of elliptic curve cryptography(ECC)and bilinear pairing(BP)*** formal security analysis is accomplished using the Burrows–Abadi–Needham(BAN)logic,demonstrating that our scheme is verifiably *** proposed scheme’s informal security assessment also shows that it provides salient security features,such as non-repudiation,anonymity,and ***,the scheme is shown to be resilient against attacks,such as packet replays,forgeries,message falsifications,and *** the performance perspective,this protocol yields a 37.88%reduction in communication overheads and a 44.44%improvement in the supported security ***,the proposed scheme can be deployed in VANETs to provide robust security at low overheads.

关键词： Attacks bilinear elliptic curve cryptography(ECC) privacy security vehicular ad hoc network(VANET)

来源：评论

学校读者我要写书评

暂无评论

A Hybrid WSVM-Levy Approach for Energy-Efficient Manufacturing Using Big data and IoT

引用

Computers, Materials & Continua 2024年第12期81卷 4895-4914页

作者： Surbhi Bhatia Khan Mohammad Alojail Mahesh Thyluru Ramakrishna Hemant Sharma School of Science Engineering and EnvironmentUniversity of SalfordManchesterM68HDUK University Centre for Research and Development Chandigarh UniversityMohali140307India Management Information System Department College of Business AdministrationKing Saud UniversityRiyadh11495Saudi Arabia Department of Computer Science and Engineering JAIN(Deemed-to-be University)Bangalore560030India Department of Computer Science and Engineering IES College of TechnologyBhopal462044India

In Intelligent Manufacturing,Big data and industrial information enable enterprises to closely monitor and respond to precise changes in both internal processes and external environmental factors,ensuring more informed decision-making and adaptive system *** also promotes decision making and provides scientific analysis to enhance the efficiency of the operation,cost reduction,maximizing the process of production and so *** methods are employed to enhance productivity,yet achieving sustainable manufacturing remains a complex challenge that requires careful *** study aims to develop a methodology for effective manufacturing sustainability by proposing a novel Hybrid Weighted Support Vector-based Lévy flight(HWS-LF)*** objective of the HWS-LF method is to improve the environmental,economic,and social aspects of manufacturing *** this approach,Support Vector Machines(SVM)are used to classify data points by identifying the optimal hyperplane to separate different classes,thereby supporting predictive maintenance and quality control in *** Forest is applied to boost efficiency,resource allocation,and production optimization.A Weighted Average Ensemble technique is employed to combine predictions from multiple models,assigning different weights to ensure an accurate system for evaluating manufacturing ***,Lévy flight Optimization is incorporated to enhance the performance of the HWS-LF method *** method’s effectiveness is assessed using various evaluation metrics,including accuracy,precision,recall,F1-score,and *** show that the proposed HWS-LF method outperforms other state-of-the-art techniques,demonstrating superior productivity and system performance.

关键词： Sustainable manufacturing support vector machine random forest levy flight optimization weighted average ensemble

来源：评论

学校读者我要写书评

暂无评论

High efficient net gain and low noise figure based vertical cavity semiconductor optical amplifiers for wavelength division multiplexing applications

引用

Journal of Optical Communications 2025年第2期46卷 247-256页

作者： Prabu, Ramachandran Thandaiah Balasubramanian, Arunsundar Balakrishnan, Nithyasundari Jebanazer, Jeneetha Kandasamy, Mohana Sundaram Govindaswamy, Nishanthi Mahmoud, Rashida Maher Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences SIMATS Saveetha University Tamilnadu Chennai India Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chennai93104 India Department of ECE S.A. Engineering College Tamilnadu Chennai India Department of ECE Panimalar Engineering College Tamilnadu Chennai India Department of CSE R.M.D. Engineering College Kavarapettai Tamilnadu Chennai India Department of CSE R.M.K. Engineering College Kavarapettai Tamilnadu Chennai India Sohag Institute of Technology Sohag Egypt

This paper has demonstrated the high efficient net gain and low noise figure based vertical cavity semiconductor light amplifiers for wavelength division multiplexing applications. Previous study on the chip reflective gain variations versus SOA current under temperature effects is clarified. We have transferred light semiconductor amplifiers for wavelength multiplexing schemes applications. Amplifier output power is demonstrated with bias current and amplifier active layer region length variations based input signal power of 3, 6.5, 10 dBm, 1550 nm wavelength and optimum amplifier confinement factor of 0.45. The amplifier output noise variations are clarified against the bias current and amplifier active layer region width variations based input signal power of 3, 6.5, 10 dBm, 1550 nm wavelength and optimum amplifier confinement factor of 0.45. The output OSNR variations are studied clearly and deeply against the bias current and amplifier active layer region length variations based input signal power of 3, 6.5, 10 dBm, 1550 nm wavelength and optimum amplifier confinement factor of 0.45. The signal loss is demonstrated versus both active layer width/length and temperature based optimum 30 % gallium core dopant ratio and 28 % arsenide cladding dopant ratio at optimum input signal power of 10 dBm, 1550 nm wavelength and optimum amplifier confinement factor of 0.45. SOA amplifier output power can be enhance with the management of both bias current and input signal power and the reduction of active amplifier length. The amplifier output noise can be enhance with the management of both bias current and input signal power and the reduction of active amplifier width. Output OSNR system can be improved with the management of both bias current and input signal power and the reduction of active amplifier length. The SOA amplifier gain can be improved with the management of both bias current and input signal power and the reduction of active amplifier length. The SOA amplifie

关键词： Noise figure

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Study Of Dynamic Thresholds Power Detection Spectrum Sensing Techniques In CRN 9

A Study Of Dynamic Thresholds Power Detection Spectrum Sensi...

引用

9th International Conference on Advanced Computing and Communication systems, ICACCS 2023

作者： Keerthika, J. AnandaKumar, H. Priya, V. Yuvalatha, S. Gayathri, N. Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India Dr NGP Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Bannari Amman Institute of Technology Department of Computer Science and Business System Sathyamangalam India

ISBN: (纸本)9798350397376

A Cognitive radio is the mobile communication technologies which help to utilize the efficient need of radio spectrum origin. The performance of CRN is significantly impacted by the spectrum sensing function. The problem of bandwidth has risen as a more specific one with breakthroughs in remote communications. By forgiving unlicensed users to usage the available spectrum in primary networks is the solution to the CR technology. An innovative method for enhancing the electromagnetic spectrum's use efficiency, cognitive radio is a encouraging technology. Spectrum sensing has high spectral resolution capabilities and aids in the detection of the spectrum holes. The various methodologies are used to enhance the spectrum sensing essence. These techniques are distinguished by a sensing threshold, which is crucial to the performance of the sensing. The most important element in selecting the best threshold to optimize spectrum sensing performance is the dynamic threshold in the proposed system's spectrum detection algorithm. The energy earned from the licensed user over a precise time of observation, then the dynamic threshold is commutated between two levels. The estimation of the noise ambiguity factor forms the basis for threshold evaluations. These criteria are used to hike the likelihood of detection and contraction the possibility of false alarms. © 2023 IEEE.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

Enhancing Customer Personality Prediction using Advanced Machine Learning Techniques and data Balancing Strategies: A Comprehensive Approach to Addressing Imbalanced datasets in Marketing Analytics 1

Enhancing Customer Personality Prediction using Advanced Mac...

引用

1st International Conference on Intelligent systems and Computational Networks, ICISCN 2025

作者： Selvalakshmi, V. Sree, T. Manju Usha Saranya, S. Devi, A. Uma Basha, Md Shaik Amzad Velammal College of Engineering and Technology Department of Master of Business Administration Madurai India Department of Master of Business Administration Hyderabad India Rajalakshmi Institute of Technology Department of Artificial Intelligence and Data Science Chennai India Alpha College of Engineering Department of Management Studies Chennai India Hyderabad India

ISBN: (纸本)9798331529246

This study tackles imbalanced customer response prediction by integrating advanced resampling methods with diverse machine learning and ensemble techniques. Novel resampling approaches (SMOTE, Borderline-SMOTE, ADASYN, and SMOTEENN) were systematically applied alongside Logistic Regression, Random Forest, Gradient Boosting, LightGBM, SVM, and Neural Networks. Stacking and voting ensembles further consolidated individual model strengths. Results show that coupling resampling with ensembles significantly boosts minority class metrics. For example, ADASYN combined with LightGBM achieved a 95% accuracy and substantially improved minority class recall and precision, while SMOTEENN with a voting ensemble reached a 99% recall, albeit with a slight precision trade-off. These findings underscore that employing sophisticated data rebalancing techniques in conjunction with hybrid ensembles can surpass traditional models, offering a balanced improvement in metrics such as accuracy, precision, recall, and F1 score. The practical significance lies in enabling more reliable predictions in highly imbalanced scenarios, ultimately enhancing decision-making processes. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing face recognition performance: a comprehensive evaluation of deep learning models and a novel ensemble approach with hyperparameter tuning

引用

Soft Computing 2024年第20期28卷 12399-12424页

作者： Selvaganesan, Jana Sudharani, B. Shekhar, S. N. Chandra Vaishnavi, K. Priyadarsini, K. Raju, K. Srujan Rao, T. Srinivasa Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R & ampD Institute of Science and Technology Avadi Tamil Nadu Chennai600062 India Guntur Dist. Andhra Pradesh Vadlamudi India Department of Electronics and Communication Engineering Sreenidhi Institute of Science and Technology Telangana Hyderabad501301 India Department of Computer Science and Engineering Sona College of Technology Tamil Nadu Salem636005 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Science and Engineering CMR Technical Campus Medchal Telangana Hyderabad501401 India Department of Electronics and Communication Engineering Aditya Engineering College Surampalem533437 India

In response to growing security concerns and the increasing demand for face recognition (FR) technology in various sectors, this research explores the application of deep learning techniques, specifically pre-trained Convolutional Neural Network (CNN) models, in the field of FR. The study harnesses the power of five pre-trained CNN models—DenseNet201, ResNet152V2, MobileNetV2, SeResNeXt, and Xception—for robust feature extraction, followed by SoftMax classification. A novel weighted average ensemble model, meticulously optimized through a grid search technique, is introduced to augment feature extraction and classification efficacy. Emphasizing the significance of robust data pre-processing, encompassing resizing, data augmentation, splitting, and normalization, the research endeavors to fortify the reliability of FR systems. Methodologically, the study systematically investigates hyperparameters across deep learning models, fine-tuning network depth, learning rate, activation functions, and optimization methods. Comprehensive evaluations unfold across diverse datasets to discern the effectiveness of the proposed models. Key contributions of this work encompass the utilization of pre-trained CNN models for feature extraction, extensive evaluation across multiple datasets, the introduction of a weighted average ensemble model, emphasis on robust data pre-processing, systematic hyperparameter tuning, and the utilization of comprehensive evaluation metrics. The results, meticulously analyzed, unveil the superior performance of the proposed method, consistently outshining alternative models across pivotal metrics, including Recall, Precision, F1 Score, Matthews Correlation Coefficient (MCC), and Accuracy. Notably, the proposed method attains an exceptional accuracy of 99.48% on the labeled faces in the wild (LFW) dataset, surpassing erstwhile state-of-the-art benchmarks. This research represents a significant stride in FR technology, furnishing a dependable and accurate

关键词： Convolutional neural networks

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：