检索结果-内蒙古大学图书馆

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Joshi, Prakash Shaikh, M.Z. Varshney, Neeraj Dwivedy, Bhoopendra Raj Kumar Goel Institute of Technology Department of Computer Science & Engineering UP Ghaziabad India Shree Bhagubhai Mafatlal Polytechnic College Department of Electronics & Telecommunication Maharastra Mumbai India Gla University Department of Computer Engineering and Applications UP Mathura India Galgotias University Department of School of Computer Science & Engineering UP Greater Noida India

ISBN: (纸本)9798350371055

Deep knowledge is the main way the improvement of gadgets, gaining knowledge of generation for more than a few applications from facial popularity to self-reliant vehicles. Deep learning fashions have carried out outstanding successes, even outperforming people in complex obligations. However, robustness demanding situations of deep getting-to-know systems remain an essential difficulty. Deep studying fashions are at risk of malicious inputs that could result in misclassifications or denial-of-provider attacks. Robustness towards entering noise, in addition to robust extraction of beneficial capabilities from noisy datasets, are just a number of the main challenges for deep mastering systems. Current research has discovered a plethora of attack vectors that can be deployed against deep getting-to-know fashions along with 'adversarial' assaults, which contain manipulating the enter records in a particular manner to purpose models to misclassify items. Moreover, dataset bias and absence of right validation can cause structures that are not sturdy towards facts from a domain extraordinary from the facts used for education. A good way to enhance the robustness of deep learning models, researchers are exploring solutions that include countermeasures, specialized architectures, and higher education and checking out approaches. While progress has been made, the robustness challenges of deep learning remain an important study vicinity that should be addressed so one can fulfill the promise of this generation. © 2024 IEEE.

关键词： Architectures Discovered Extraordinary Manipulating Researchers

来源：评论

学校读者我要写书评

暂无评论

Future Database Technologies for Big Data Analytics

Future Database Technologies for Big Data Analytics

引用

2023 International Conference on Intelligent Systems for Communication, IoT and Security, ICISCoIS 2023

作者： Rani, Geeta Sharma, Taruna Sharma, Avinash Chitkara University Institute of Engineering and Technology Dept of Computer Applications Punjab India Maharishi Markandeshwar Engineering College Department of Computer Science and Engineering Mullana India

ISBN: (纸本)9798350335835

Data is valuable asset for organizations but it cannot be used directly for business decision making. It needs to be processed in a form that is easily understandable and can to be used by decision makers. The database technology is continuously changing as the data is growing at a rapid date and business requirements change with time. With the advent of IOT, social media and other technology advancements, data become more complex in terms of volume, variety and veracity. Traditional technology can't be used for handling this data due to its complex and dynamic nature of Big Data. So more advanced and sophisticated tools are essential to handle complex nature of data. In this paper the various database tools are discussed and analysed by different vendors which are suitable for big data Analytics. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Securing the Cyber Supply Chain: A Risk-based Approach to Threat Assessment and Mitigation 4

Securing the Cyber Supply Chain: A Risk-based Approach to Th...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Phani Prathyusha, J.R.V.S.L.P. Esther Jyothi, V. Jhansi, Vadlamudi Sampreeth Chowdary, N. Madhuri, A. Sindhura, S. Velagapudi Ramakrishna Siddhartha Engineering College Department of Computer Applications Vijayawada India P.V.P. Siddhartha Institute of Technology Department of Computer Science and Engineering Vijayawada India Nri Institute of Technology Department of Computer Science and Engineering Agiripalli India

ISBN: (纸本)9798350300093

The system of Cyber Supply Chain (CSC) is characterized by its complexity, consisting of several subsystems, each responsible for a distinct set of responsibilities. Securing the supply chain presents a challenge due to the presence of vulnerabilities and threats throughout the system that has the potential to be taken advantage of at any time, considering that any component of the system is susceptible to such attacks. As a result, supply chain security is difficult to achieve. This has the potential to create a significant interruption to the overall continuity of the company. Therefore, it is of the utmost importance to identify the hazards and make educated guesses about their likely outcomes so that organizations can take the appropriate precautions to ensure the safety of their supply chains. By leveraging a range of factors, such as the expertise and incentives of threat actors, Tactics, Techniques, and Procedures (TT and P), as well as Indicators of Compromise (IoC), the analysis of Cyber Threat Intelligence (CTI) offers valuable information on both identified ansignd unidentified cybersecurity threats. In order to increase the safety of the cyber supply chain, the purpose of this article is to investigate and speculate on potential dangers. The CTI and Machine Learning (ML) approaches have been employed by us in order to study and forecast the risks based on the CTI attributes. This makes it possible to detect the inherent CSC vulnerabilities, which enables suitable control. To enhance the overall security of computer systems, it is imperative to implement specific actions, including the collection of CTI data and the adoption of various machine learning techniques. These techniques encompass Logistic Regression (LG), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Cat Boost, and Gradient Boost, which are employed in analyzing the Microsoft Malware Prediction dataset to create predictive analytics. This is done in order to illustrate t

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Automated Knowledge Transfer for Medical Image Segmentation Using Deep Learning

Automated Knowledge Transfer for Medical Image Segmentation ...

引用

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Tyagi, Priya Masson, Palak Jain, Ayushi Varshney, Neeraj Verma, Aditya Nitra Technical Campus Department Of CSE-AIML UP Ghaziabad India Raj Kumar Goel Institute Of Technology Computer Science & Engineering UP Ghaziabad India Graphic Era Hill University Computer Science & Engineering Uttarakhand Dehradun India Gla University Department Of Computer Engineering And Applications UP Mathura India Graphic Era Deemed To Be University Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350366846

The usage of deep trends for scientific photograph segmentation has seen a speedy increase in recognition in recent years of today's capability to generate accurate photo segmentation fashions. However, the development and deployment of these fashions may be time-eating and highly-priced state-of-the-art to engineer features and architectures for each project manually. Automatic knowledge transfer (AKT) can address this difficulty by presenting a manner to switch knowledge throughout distinct duties while requiring minimal guide attempts. AKT can obtain better effects than guide engineering procedures by extracting the most pertinent knowledge from present fashions and applying it to the goal project. It leads to a generalizable and fee-effective answer. These paper overviews the AKT and talk capability programs for medical picture segmentation. We survey the latest publications on the subject and discuss modern trends and challenges inside the place. We provide a top-level view of the latest three unique processes to AKT- transfer latest, meta-today, and self-supervised modern-day - and highlight how they can be used to obtain successful medical photo segmentation. Finally, we discuss future guidelines for research in this discipline. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Security Challenges in Multi-Cloud Environments: Solutions and Best Practices 7

Security Challenges in Multi-Cloud Environments: Solutions a...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Madanan, Mukesh Patel, Pratik Agrawal, Prateek Mudholkar, Pankaj Mudholkar, Megha Jaganraja, V. Dhofar University Department of Computer Science Oman National Forensic Sciences University India India Marwadi University Faculty of Computer Applications Gujarat Rajkot360003 India Marwadi University Department of Computer Engineering Gujarat Rajkot360003 India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Chennai600062 India

ISBN: (纸本)9798350350067

The aim of this research paper is to investigate how machine learning can be incorporated to improve security around multi-clouds, with specific reference to the challenges. Based on the datasets obtained from Kaggle, this study uses both unsupervised learning, more specifically the Isolation Forest technique and supervised learning, such as regression-based forecast for identifying possible security threats. The evaluation shows that through the use of ML techniques risk that originates from multi-cloud systems may be well managed while, at the same time, the utilization of cloud resources could be enhanced to produce the best results. The results make it possible to conclude that machine learning still holds a huge potential in the sphere of cloud security and provides a range of recommendations and recommendations for organizations that have to manage their multi-cloud environment. Possible future studies are devoted to the investigation of deep learning models and the incorporation of blockchain technology for more security and effectiveness of the system. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Role of internet of things in protecting different wearable gadgets and materials

引用

Materials Today: Proceedings 2022年 56卷 3387-3393页

作者： Prasant, P. Bhardwaj, Shashank Gupta, Monisha Srivastava, Mahima Singh, Jitendra Maurya, Rajesh Kumar Computer Science and Technology Khalsa College of Engineering and Technology Amritsar India Department of Computer Applications KIET Group of Institutions Ghaziabad India Computer Science and Engineering Chandigarh University Punjab India College Uttarakhand Dehradun India Department of Computer Science Engineering SRM Institute of Science and Technology UP Ghaziabad India MCA ABES Engineering College Ghaziabad India

Out of the most entrusted technological revolutions applied for the advancement of living standards and creation of a more convenient operation in the professional world, the Internet of Things (IoT) has been progressing at the highest projected pace. The interconnectivity of gadgets and devices over the internet to produce smarter control, communication, and a swift and easy lifestyle makes it an amazing tech introduction. However, the IOT also brings along a huge flow of privacy and security concerns whilst considering the huge inflow of data breaches and cyberattacks in the network data. The advancements in the security protocols of the data thus bring along mistrust among the users of IoT networks who might then no longer wish to be a part of this technological revolution. Therefore, it is important to maintain security assurance in the IoT based connection networks of wearable gadgets. This paper discusses the symmetric and asymmetric approaches of encryption over IoT which can help protect the network of smart phones connected to the wearable to assure a safe and smart data commute and avoid access to private data over the same internet connection. © 2021

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Impact of Model Selection on Pulmonary Effusion Diagnosis Using Prediction Analysis Algorithms

Impact of Model Selection on Pulmonary Effusion Diagnosis Us...

引用

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Mani, Chandra Pachauri, Divya Gupta, Richa Varshney, Neeraj Manwal, Manika Raj Kumar Goel Institute Of Technology Computer Science & Engineering UP Ghaziabad India Nitra Technical Campus Department Of CSE-AIML UP Ghaziabad India Graphic Era Hill University Computer Science & Engineering Uttarakhand Dehradun India Gla University Department Of Computer Engineering And Applications UP Mathura India Graphic Era Deemed To Be University Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350366846

Model selection is of utmost significance for accurate analysis and treatment of pulmonary effusion. With the increasing complexity of scientific statistics and the advancement of prediction analysis algorithms in the clinical field, model selection has emerge as a critical step in a hit prediction evaluation. In this text, we have a look at the effect of version choice on pulmonary effusion prognosis the use of a hard and fast of prediction evaluation algorithms. We compare the overall performance of different algorithms in phrases of accuracy, kind-I and sort-II errors, and interpretability. We demonstrate that version selection can have an effect on the accuracy and interpretability of the diagnosis and for this reason the remedy plan installed for the patient. We in addition talk the consequences for practitioners, clinicians, and researchers, who have to don't forget the deserves of model choice whilst the use of prediction analysis algorithms for the analysis of pulmonary effusion. Version choice is a crucial a part of the predictive evaluation pipeline, as the selection of version for given software may have a large effect on accuracy and performance. In the context of pulmonary effusion (PE) analysis, an appropriate choice of a predictive evaluation set of rules can enhance the detection of PE abnormalities and facilitate scientific decision making. Numerous algorithms were carried out to broaden models for PE prognosis, which includes synthetic neural networks, help vector machines, logistic regression, and decision trees. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Detection of Animal Hunters in Forest Using Regional Convolutional Neural Network Algorithm

Detection of Animal Hunters in Forest Using Regional Convolu...

引用

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Sakthivanitha, M. Lakshmi, R.Bagavathi Chitra, A. Priscila, S.Silvia Department of Information Technology Chennai India Drbccc Hindu College Department of Computer Applications Chennai India Bharath Institute of Higher Education and Research Department of Computer Science Chennai India

ISBN: (纸本)9798350317060

Detection of objects moving in a video is regarded as a vital problem in image processing applications i.e. the detection during the movement of camera is considered significant in video processing. In this paper, the movable objects for instance humans moving in forest environment is detected using a deep learning algorithm called regional convolutional neural network (RCNN). In this classification model, the classifier segregate the moving human in a dynamic environment. The region of motion is initially detected via background compensation method. The RCNN is utilised then to locate accurate the person moving in that region of motion. The RCNN model is a lightweight classifier that is designed specifically for the smaller objects. The results of both motion and object detection is fused together to obtain the moving objects. If a moving information is missed in the current frame, it is then recalled in the subsequent frame as per the spatial or temporal data. The simulation is conducted on 30 videos, where 24 is used for training the classifier and remaining 6 is taken for testing purposes. The result of simulation shows that the proposed RCNN model obtains improved accuracy, specificity, sensitivity and f-measure. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Implementation of Ensemble Predictive Models for Parkinson’s Disease Detection 5th

Implementation of Ensemble Predictive Models for Parkinson’...

引用

5th International Conference on Advances in Information Communication Technology and Computing, AICTC 2024

作者： Ruth, J. Anitha Mahesh, Vijayalakshmi G. V. Uma, R. Department of Computer Science and Applications SRM Institute of Science and Technology Vadapalani Campus Tamil Nadu Chennai India Department of Electronics and Communication BMS Institute of Technology and Management Karnataka Bengaluru India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Chennai India

ISBN: (纸本)9789819761029

A framework based on ensemble classifier models is presented in this study, which may be used to predict the presence of disease and to increase the accuracy of the prediction. Machine learning's ensemble technique pools several different classification algorithms and an extensive number of classifier models to get more precise predictions. In this present study SVM and DT are employed as base estimators, which takes use of well-known ensemble techniques, such as bagging and boosting, to construct ensemble classifiers. The proposed technique is tested on a Parkinson's database taken from machine learning repository and is found to be effective. Classification accuracy (CA), precision, recall, area under curve (AUC), Cohen kappa score (CKS), Mathews correlation coefficient (MCC), and F1-measure obtained from receiver operating characteristics (ROC), as well as the MCC and F1-measure indicate that the ensemble classifier model has enhanced prediction performance with the least possible errors. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Meme Expressive Classification in Multimodal State with Feature Extraction in Deep Learning 2

Meme Expressive Classification in Multimodal State with Feat...

引用

2nd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2023

作者： Barveen, A. Geetha, S. Faizal, M.K.Mohamed M.I.E.T. Engineering College Department of Computer Science and Engineering Trichy India University College of Engineering Department of Computer Applications Tamilnadu Trichy India

ISBN: (纸本)9798350397635

Memes are a socially interactive way to communicate online. Memes are used by users to communicate with one another on social networking sites and other forums. Memes essentially focus on speech recognition and image macros. While a meme is being created, it focuses on the semiotic type of resources that the internet community interprets with other resources, which facilitates the interaction among the internet and meme creators. Memes recreate based on various approaches, which fall under various acts such as existing speech acts. Based on the expressive face with captioned short texts, even the short text is exaggerated. Every year, meme mimicking applications are created that allow users to use the imitated meme expressions. Memes represent the shared texts of the younger generations on various social platforms. The classifications of sentiment based on the various memetic expressions are the most efficient way to analyse those feelings and emotions. HOG feature extraction allows the images to be segmented into blocks of smaller size by using a single feature vector for dimension, which characterizes the local object appearances to characterize the meme classification. The existence of specific characteristics, including such edges, angles, or patterns, is then analyzed by combining HOG features using multi-feature analysis on patches. Based upon the classification methodology, it classifies the sentiments, which tend to improve the learning process in an efficient manner. By combining a deep learning approach with a recurrent neural network, the extended LSTM-RNN can identify subtle nuances in memes, allowing for more accurate and detailed meme classification. This proposed method effectively evaluates several classification techniques, including CNN and Extended LSTM-RNN for meme image characterization. Through training and validation, Extended LSTM-RNN achieved 0.98% accuracy with better performance than CNN. © 2023 IEEE.

关键词： Feature extraction

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：