检索结果-内蒙古大学图书馆

6th International Conference on Smart Cities, Internet of Things and Applications, SCIoT 2022

作者： Afshar, Bahar Fathy, Mahmood Asgari, Maryam Shahverdy, Mohammad Shahverdi, Pooya Islamic Azad University Professor Hessabi Branch Department of Computer Engineering Tafresh Iran Iran University of Science and Technology Department of Computer Engineering Tehran Iran

ISBN: (数字)9781665488914

ISBN: (纸本)9781665488914

After the increase of pollution caused by vehicle congestion, new approaches to reduce pollution have emerged. Although regular visits to technical inspection centers and car repair center can be helpful, a new approach is to achieve effective integration between mobile applications and vehicles. This integration can be achieved using the ELM327 interface, which provides data such as speed, fuel consumption, gas emission, and system failure using the wireless interface to the mobile phone. Nowadays, vehicles have to go to technical inspection centers for pollution testing, which is costly in terms of time and price. This paper presents a machine learning-based method that uses data extracted from vehicle sensors and can determine the amount of pollution emitted from vehicle then warns the driver. Experimental results confirm that the proposed method can efficiently detect Polluting Vehicles. © 2022 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Mitigating Credit Card Fraud: A Machine Learning Perspective

Mitigating Credit Card Fraud: A Machine Learning Perspective

引用

Recent Trends in Microelectronics, Automation, Computing and Communications Systems (ICMACC), International Conference on

作者： Shivam Bhushan Indrajeet Gupta Angayarkanni S A Balakiruthiga B Pandimurugan V Rajaram V Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattankulathur India Associate Professor Computer Science and engineering Acharya Institute of Technology Bangalore India

ISBN: (数字)9798350366570

ISBN: (纸本)9798350366587

In this day and age of online and digital transactions, credit cards have come up as a popular option of payment. This has led to the increase in the fraudulent credit card transactions and as a result the banks and the customers have to bear the loss. It is very vital for the credit card companies to identify and stop the fraud transactions. The main aim of this project is to create a model that can distinguish fraudulent credit card transactions from real ones. The proposed model uses the transaction patterns of previous credit card transaction data which contains both genuine and fraud data to train itself using suitable ML algorithms and identify the fraudulent transactions and nip it in the bud. We will be using using SMOTE to process the data considering the imbalance between legitimate and fraudulent transactions, hyperparameter tuning the model for increased effectiveness and using random forest classifier and decision tree classifier to compare results. By using the above mentioned techniques we saw an increase in accuracy and recall. These models offer a scaleable solution to the problem of real time fraud detection in an ever growing and vast financial landscape

关键词： Machine learning algorithms Accuracy Credit cards Data models Real-time systems Fraud Microelectronics Random forests Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Learning Framework using CapsNet and SOM for Multidrug-Resistant Tuberculosis Detection and Analysis in CXR Images

引用

Procedia computer science 2025年 258卷 3251-3263页

作者： Ceronmani Sharmila V Remya K Sam Praveen P Associate Professor Department of ECE SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu Assistant Professor Department of Information Technology Hindustan Institute of Technology and Science Padur Chennai Tamil Nadu PG Student Department of Computer Science and Information Systems Birla Institute of Technology and Science Pilani Rajasthan

Early detection of Multidrug-resistant Tuberculosis (MDR-TB) is crucial for illness prevention, lowering mortality risk, and preventing the spread of infection to people. The chest X-ray images(CXRI), which is affordable and widely available data can be used for MDR-TB disease screening in clinics. However, radiologists must manually review CXRI, which places a significant strain on them and increases inter-observer variability. Therefore, it is difficult for researchers to suggest a reliable and affordable CAD method for detecting MDR-TB. In this study, Capsule Neural Networks and Self Organizing Maps, simple and effective deep learning networks were introduced to perform detection and analysis tasks respectively. CapsNet is used to reliably identify MDR-TB from the patient’s CXR images. SOM clusters and visualizes the data at each layering stage. This work proposes an innovative approach of fusing CapsNet and SOM to produce higher accuracy. Comparative analysis between three classification methods under CapsNet (Dynamic routing, Transformation matrix, Convolutional capsules) is also performed. ConvCaps outperformed than the other two methods with the accuracy of 89.47%. The model is assessed by few parameters such as Precision, Recall, Accuracy, and F1-score for each method. The accuracy of the proposed fused CapsNet and SOM model is 93.6%.

关键词： CapsNet Multidrug-resistant Tuberculosis SOM CXR Images

来源：评论

学校读者我要写书评

暂无评论

Blockchain effect on E-commerce: A framework for key research areas

Blockchain effect on E-commerce: A framework for key researc...

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Nethravathi, K. Panduro-Ramirez, Jeidy Gehlot, Anita Barve, Amit Sanjay, C.P. Ponnusamy, R. Jain University Department of Bms Bangalore India Universidad Tecnológica Del Perú Peru Uttaranchal University Uttaranchal Institute of Technology India Parul University Department of Associate Professor & Hod India Department of It& Business Analytics India Chennai Institute of Technology Department of Computer Science & Engineering India

ISBN: (纸本)9798350322309

Several business applications and procedures are expected to be significantly disrupted by Blockchain-based technologies, which has significant consequences for ecommerce. In light of the potential blockchain based technology are popularly known as "trust building systems"that can be used in multiple business models and standard guidelines which evolved placed above a white period to achieve believe, serviceability, and enforcement in various domains such as cunsumers related business, business related connections have to be questioned and possibly adjusted. By enabling trustless trade interactions that work without specialized intermediaries or even central authority in the case of permission lessblock chains, Blockchain has the power to change how electronic commerce operates. Furthermore, giving universal access to immutable data across the whole supply chain may significantly alter the information and value exchange between businesses and consumers. The methodology presented in this paper are intended to motivate further study of the potential effects of Blockchain on e-commerce. Technology, law, organizational and quality challenges, as well as consumer difficulties, are the four key categories. This paper demonstrates how Blockchain may affect many Electronic commercial components in these relevant fields. © 2023 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Cerebral Splitting: Adaptation for Spine Elimination

Deep Learning Cerebral Splitting: Adaptation for Spine Elimi...

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： M. Balasubramani B. J. Job Karuna Sagar K. C. Rajheshwari E. Saranya B. Aishwarya P. Murugeswari Assistant Professor Department of Computer Science and Engineering V.S.B. Engineering College Professor Department of Computer Science and Engineering Joginpally B.R Engineering College Hyderabad India Department of Computer Science and Engineering Sona College of Technology Assistant Professor Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore Assistant Professor Department of Computer Science and Engineering(Cyber Security) Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Department of Electronics and Communication Engineering Theni Kammavar Sangam College of Technology

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

The posterior fossa volume and the total intracranial volume are important factors to consider when doing a brain volumetric analysis using structural electromagnetic resonance imaging. The thorough segmentation of the whole cortex offers a method for non-invasively evaluating different brain regions. In addition, the extraction of skulls in a way that maintains anonymity is increasingly being used as a means of disseminating large amounts of data obtained from brain images. Therefore, generalizing machine learning brain regions for intracranial measurements after skull removal is an interesting task. However, data collecting is difficult due to the small number of handwritten and whole-brain atlases marked with his TICV/PFV. In this study, we use U-Net tiles to estimate intracranial volume and perform whole-brain segmentation with and without cranial characteristics simultaneously. In the absence of individually recorded total cortical volume, a transfer learning approach has been shown to estimate extra her TICV and PFV labeling during whole-brain delineation on T1-weighted MRI. More specifically, U-Net tiles are pre-trained using a big Brain COLOR atlas generated using multi-atlas segmentation, and do not include his PFV labels. The pre-trained model is improved to learn more His TICV and PFV labels using the limited Brain COLOR atlas. We also elaborate on his method for processing MR images of the brain in the absence of a skull. The results show that our method produces reasonable segmentation and size estimation results in terms of average contact distance, cubic similarity index, and total volumetric similarity for both brains within and outside the skull. is showing off. This technology is currently available as open source to the general public.

关键词： Deep learning Image segmentation Image color analysis Magnetic resonance imaging Transfer learning Pipelines Estimation Skull Resonance Telecommunication computing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques Advancements in Apple Leaf Disease Detection

引用

Procedia computer science 2024年 235卷 713-722页

作者： E Kannan Carmel Mary Belinda M J Alex David S Ruth Naveena N Almas Begum Hemalatha D Professor Assistant Professor Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India 600062 Professor Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical And Technical Sciences Chennai Tamilnadu India 602105 Assistant Professor (SG) Hindustan Institute of Technology and Science Chennai Tamilnadu India 603103 Assistant Professor Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India 600062

An exhaustive and comprehensive investigation was undertaken to address the critical issue of disease detection on apple leaves using cutting-edge deep learning techniques. The research delved into an array of diverse approaches, meticulously examining their efficacy and performance in disease detection, ultimately offering valuable insights into this vital domain. The research effort was marked by the exploration and application of a wide spectrum of deep learning models, each chosen for its distinct characteristics and potential advantages. The results of this extensive work were nothing short of remarkable. This study uses state-of-the-art deep learning techniques to present a thorough and rigorous analysis into the important problem of disease detection on apple leaves. Our research covers a wide range of approaches, all of which have been thoroughly assessed for their efficacy in the diagnosis of disease. We used a wide range of deep learning models, selected for their special qualities and possible benefits. The results of this extensive study are impressive and measurable. VGG-INCEP, the top approach, showed exceptional performance with a measured accuracy rate of 97%. The quantification of precision, recall, and F1 scores were 0.94, 0.92, and 0.92, respectively. Similarly, InceptionV3 yielded an F1 score of 0.93, precision of 0.95, and recall of 0.91, in addition to a measured accuracy of 97%. AlexNet consistently demonstrated measurable high precision (0.95) and recall (0.93), resulting in an F1 score of 0.93, despite a somewhat lower accuracy of 87%. The method's balanced performance is highlighted by these metrics. The study also evaluated the effectiveness of SVM, MobileNet, RCNN, and a recommended method. With quantifiable accuracy of 98% and quantifiable precision, recall, and F1 scores of 0.96, the suggested technique stood out. This assessment unequivocally shows that the suggested approach produces the best accuracy and overall performance and is di

关键词： Apple leaf diseases Deep learning Disease detection Precision agriculture Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Lamport Blum Shub Signcryptive Extreme Learning Machine for Secure Transmission of Digital Images

引用

Procedia computer science 2025年 252卷 728-737页

作者： V. Prabavathi M. Sakthi Research Scholar Department of Computer Science Nallamuthu Gounder Mahalingam College Affiliated to Bharathiar University Pollachi Tamil Nadu India Associate Professor Department of Computer Science Nallamuthu Gounder Mahalingam College Affiliated to Bharathiar University Pollachi TamilNadu India

Image transmission refers to sending or transferring digital images from one location to another, typically over a network or communication channel across various domains, including telecommunications, multimedia messaging, surveillance systems, medical imaging, remote sensing, etc. However, with growing popularity of digital skills, ensuring safety and integrity of transmitted images has become a significant concern. For increasing security, Machine learning and cryptographic techniques have been discussed. Nevertheless, confidentiality during image transmission faces major challenges. Proposed Lamport Blum ShubSigncryptive Extreme Learning (LBSSEL) Method is introduced for secured image transmission with minimal time consumption. The Extreme Learning machine comprises different layers. Several natural images gathered as of dataset. The input layer receives these images for secure transmission. The proposed cryptographic method performs key generation, signcryption, as well as unsigncryption. Lamport One-Time Digital signature method applied in first hidden layer to generate key pairs. Signcryption carried out in second hidden layer which includes encryption and digital signature. For secured transmission, an encrypted image (i.e., cipher image) as well as signature broadcast to receiver to preserve input image. In third hidden layer, unsigncryption process carried out for receiving original image by authorized users through signature verification and decryption. Finally, confidentiality is improved during image transmission at the output layer. Simulation estimated with dissimilar factors. Outcomes of LBSSSEL model in terms of achieving maximum PSNR, confidentiality during transmission, with minimal time consumption when compared with existing approaches.

关键词： Image transmission security Signcryption Extreme Learning Lamport One-Time Digital signature method Blum Shub pseudorandom number generator

来源：评论

学校读者我要写书评

暂无评论

Confidential machine learning on untrusted platforms:a survey

引用

Cybersecurity 2021年第1期4卷 461-479页

作者： Sharma Sagar Chen Keke Northwestern Mutual Data Science Associate Professor Director of Trustworthy and Intelligent Computing Lab Department of Computer Science Marquette University Milwaukee WisconsinUSA HP Inc. USA

With the ever-growing data and the need for developing powerful machine learning models,data owners increasingly depend on various untrusted platforms(e.g.,public clouds,edges,and machine learning service providers)for scalable processing or collaborative ***,sensitive data and models are in danger of unauthorized access,misuse,and privacy compromises.A relatively new body of research confidentially trains machine learning models on protected data to address these *** this survey,we summarize notable studies in this emerging area of *** a unified framework,we highlight the critical challenges and innovations in outsourcing machine learning *** focus on the cryptographic approaches for confidential machine learning(CML),primarily on model training,while also covering other directions such as perturbation-based approaches and CML in the hardware-assisted computing *** discussion will take a holistic way to consider a rich context of the related threat models,security assumptions,design principles,and associated trade-offs amongst data utility,cost,and confidentiality.

关键词： Confidential computing Cryptographic protocols Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Effective Lightweight Homomorphic Cryptographic Algorithm for data security in cloud computing

引用

International Journal of Intelligent Networks 2022年 3卷 16-30页

作者： Thabit, Fursan Can, Ozgu Alhomdy, Sharaf Al-Gaphari, Ghaleb H. Jagtap, Sudhir Postdoctoral Researcher Department of Computer Engineering Faculty of Engineering Ege University Turkey Assoc. Prof Dr. Department of Computer Engineering Faculty of Engineering Ege University Turkey Sana'a University Yemen Professor and Principal Research Centre of Computer Science S.V.M Campus - S.R.T.M. University India

Cloud computing is a technology in which the resources are delivered as services. Users can access them anywhere, anytime via the Internet without any need to know the infrastructure knowledge, experience, or even authority that provides such services. It has become an important medium for enterprises to develop their networks because of these resources. With the growing need for cloud computing, security is becoming important for both individuals and business needs. Many researchers have studied the security of cloud computing. Still, security gaps or threats are increasing as the demand for cloud computing connectivity increases. Because a third party mostly provides cloud platforms to the cloud client, data protection in the cloud is the primary issue. This paper presents a novel, effective lightweight homomorphic cryptographic algorithm which contains two layers of encryption. The first layer uses the new effective, light-weight cryptographic algorithm and the second layer multiplicative homomorphic schemes considered for improving security data in cloud computing. This approach offers both symmetric and asymmetric cryptography features. The proposed approach's performance is evaluated using a variety of metrics, including memory, computational time and (key sensitivity), statistical analysis, image histogram, and entropy change analysis. The proposed algorithm's experimental findings showed a high level of security and an apparent improvement in encryption execution time, memory usage, and throughput. When compared to the cryptographic systems widely used in cloud computing. © 2022 The Authors

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A Review on Vulnerabilities to Modern Processors and its Mitigation for Various Variants

引用

Procedia computer science 2022年 215卷 91-97页

作者： E Praveen Kumar S Priyanka T Sudhakar Associate Professor School of Computer Science and Engineering VIT-AP University Amaravathi India

Recently, security researchers have found two hardware security vulnerabilities namely Spectre and Meltdown, related to computer memory. They are not singular, many variants of these two vulnerabilities are being a head ache for secure hardware designers. These attacks affect the modern CPUs which use speculative and out-of-order execution for optimization. This attack may affect the computing device which using the processor like Intel, AMD, ARM, and other processors like ARM processors that may use by mobile devices. By exploiting these attack that may allow the adversary to gain the control of a device to capture all the secrete data available on the system or a memory. These vulnerabilities need the better solution at the hardware level, but the problem is hardware updates is not possible at the real-time. In the face, the software-based solution is not addressed by the long run to avoid this attack, this solution is only for time constrain. This paper presents the solution for different variants of Spectre and Meltdown vulnerabilities and how they are dangerous to the modern processors like Intel, AMD, and so on to avoid the damage of the hardware using Hardware Performance Counters (HPCs). Finally, some of the mitigation techniques against these vulnerabilities are suggested based on the running application of a device.

关键词： Spectre Meltdown Processors Vulnerability attacks AMD INTEL Mitigation Technique HPCs

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：