检索结果-内蒙古大学图书馆

3rd International Conference on advanced Computing and Applications, ICACA 2024

作者： Mandal, Diptarka Ray, Amartya Sarkar, Sujan Ojjela, Odelu Sarkar, Ram School of Computer Engineering and Mathematical Sciences Defence Institute of Advanced Technology Maharashtra Pune411025 India Department of Computer Science and Engineering Jadavpur University West Bengal Kolkata700032 India

ISBN: (纸本)9789819747986

Skin cancer ranks among the deadliest forms of cancer worldwide, leading to numerous fatalities annually. Hence, the development of efficient computer-aided diagnosis (CAD) systems has become a pressing need to help medical professionals classify various types of skin cancer. This paper introduces a novel method which combines the outcomes of two deep learning models, leveraging the feature fusion strategy. Our approach utilizes Xception and Google’s Big Transfer (BiT-M) model as base learners, complemented by a squeeze and excitation attention module to enhance the fused feature maps. We also establish a combined loss function to optimize our model. We have evaluated the model on the challenging ISIC 2017 dataset and obtained an impressive accuracy of 0.795, surpassing the performance of many recently published methods within the literature. The source code of the proposed model is available at https://***/Cmatermedicalimageanalysis/ISIC2017. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Harnessing the Potential of the Internet of Things: Navigating Choices Between Fog and Cloud Infrastructure in Agriculture 2nd

Harnessing the Potential of the Internet of Things: Navigati...

引用

2nd International Conference on Cyber Intelligence and Information Retrieval, CIIR 2023

作者： Singh, Malikhan Arora, Kavita Pathak, Sonal Quraishi, Suhail Javed Singh, Anupam Ather, Danish Computer Science and Engineering Modern Institute of Technology and Research Centre Rajasthan Alwar India School of Computer Applications Manav Rachna International Institute of Research and Studies Haryana Faridabad India Department of Computer Science and Engineering Graphic era Hill University Dehradun India Amity University in Tashkent Tashkent Uzbekistan

ISBN: (纸本)9789819776023

In recent years, the Internet of Things (IoT) has become a pivotal force in transforming various sectors, with agriculture being a prominent beneficiary. The integration of smart devices, sensors, and data-driven decision-making tools has led to the emergence of a more efficient and sustainable farming landscape. Central to this transformation is the decision of where and how to process and store the vast amounts of data generated by these devices. This paper delves into the practical implications of fog and cloud computing systems in the agricultural domain taking Delhi NCR and region as a sample area by considering factors like efficiency, scalability, and real-world challenges faced by farmers. The aim here is to provide a comprehensive guide to stakeholders in making an informed choice between fog and cloud infrastructure for their IoT-enabled agricultural endeavors. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Secure Multi-Party Computation for Collaborative Data Analysis in Network Security 2

Secure Multi-Party Computation for Collaborative Data Analys...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Tamilselvi, P. Lathika, V. Jayachitra, S. Arunkumar, S. Balasubramani, M. Kalaichelvi, V. Vels Institute of Science Technology and Advanced Studies Department of Computer Science and Engineering Chennai India Department of Cse Salem India Psna College of Engineering and Technology Department of Ece Dindigul India Coimbatore Institute of Engineering and Technology Department of Ece Coimbatore India Vsb Engineering College Department of Computer Science and Engineering Karur India Sastra Deemed to Be University Srinivasa Ramanujan Centre Department of Cse Kumbakonam India

ISBN: (纸本)9798350306415

Within the scope of this research, we provide a Secure Multi-Party Computation (SMPC) architecture that has been adapted specifically for the purpose of collaborative data analysis in network protection. Significant improvements have been made to the framework in terms of performance metrics, security, and applicability in the real world. When measured against a baseline, comparative analysis showed a notable reduction of 25% in execution time, a decrease of 20% in communication overhead, and a drop of 16.67% in computational complexity. These enhancements highlight the framework's efficiency advantages, which are vital for maximising responsiveness and scalability in collaborative efforts to improve network security. As a result of the security evaluation, which demonstrates a shift from moderate to high privacy preservation, strong resilience to assaults, and low sensitivity to parameters, the suggested framework has been shown to be reliable. Real-world application scenarios further emphasise its adaptability, showing that its influence on threat intelligence sharing is moderate, while its impact on collaborative incident response is significant, and its impact on vulnerability analysis is low. These findings, when taken as a whole, establish the SMPC framework as a useful resource for organisations that want to improve the effectiveness of their joint efforts to secure networked environments. The research places a strong emphasis on the practical importance of the framework, which helps to build enhanced trust, collaboration, and resilience against developing cyber threats. Assessments of scalability, improvements to cryptographic protocols, and interaction with newly developing technology are some potential future topics for study. advanced threat analysis may also benefit. © 2024 IEEE.

关键词： Collaborative Data Analysis Cryptographic Protocols Network Security Privacy Preservation Secure Multi-Party Computation (SMPC)

来源：评论

学校读者我要写书评

暂无评论

Novel Lung Cancer Classification and Segmentation Algorithm with Web UI Interface 6

Novel Lung Cancer Classification and Segmentation Algorithm ...

引用

6th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2022

作者： Divya, M. Sathya, S. Vels Institute of Science Technology and Advanced Studies Hcas Department of Computer Science Erp Department India Vistas Department of Bca and It India

ISBN: (纸本)9781665482714

For humans, it is difficult and time-consuming to use Computed Tomography (CT) pictures to identify lung illnesses. This research work develops a novel algorithm for segmenting the cancer part in the lung and an algorithm is enhanced to classify the lung cancer images. MediNet is a segmentation-based algorithm, used to segregate the cancer-affected region from an unaffected region in the CT image whereas LuNet is the algorithm developed by enhancing an algorithm to achieve the classification of the type of cancer. This MediNet algorithm involves layers such as thirty convolutional layers, three maxpooling layers, and three bi-directional convolutional layers. By obtaining 97% accuracy, MediNet outperformed other models. Besides this, a web application is also developed to assist the doctor with a UI interface. This is developed in such a way that the doctor can upload a cancerous or non-cancerous scan in the application which will be linked to the developed classification and segmentation algorithm Medinet and LuNet. Thebackend will be running in a server that will take the input from the web app and process the output and return back the results to the web application in terms of the presence or absence of cancer as well as segmented cancerous areas in case of presence of cancer. © 2022 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Radial Basis Function Networks for Image Restoration with Stochastic Normalizations as Bayesian Learning in Deep Conventional Neural Network 6

Radial Basis Function Networks for Image Restoration with St...

引用

6th International Conference on Computing Methodologies and Communication, ICCMC 2022

作者： Senthilkumar, V. Jayalakshmi, V. Vels Institute of Science Technology and Advanced Studies Dept. of Computer Science Chennai India

ISBN: (纸本)9781665410281

The objective of the image restoration process is to improve the high-quality visual resolution from degraded images using various techniques in Artificial Intelligence., utilizing a normalization method, a method of centers and weights that has been adapted from the Radial Basis Function Network (RBFN) is initiated to the Stochastic Normalizations method as a Bayesian Learning algorithm. The normalized form of the RBFN-SB algorithm is derived, and the RBFN input data vector is from a damaged image array raised using Taylor's expansion. Following the dynamics of the normalized technique appeared to be tactful in comparison with the RBFN-SB. The test performance comparable to BN and, concomitantly, better validation losses suitable for ensuring results unpredictability estimation through approximate Bayesian posterior are procured. To test the outcome of the proposed system gave speed up the learning process, with minimum mean squared error (MSE) and produced better results of restoration images from damaged images. In the same form, the normalization accuracy can also be improved notably by the Bayesian learning algorithm. © 2022 IEEE.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Metric Identification of Vertices in Polygonal Cacti

引用

computer Modeling in Engineering & sciences 2023年第7期136卷 883-899页

作者： Xiujun Zhang Muhammad Salman Anam Rani Rashna Tanveer Usman Ali Zehui Shao School of Computer Science Chengdu UniversityChengduChina Department of Mathematics The Islamia University of BahawalpurBahawalpurPakistan Centre for Advanced Studies in Pure and Applied Mathematics Bahauddin Zakariya UniversityMultanPakistan Institute for Intelligent Information Processing South China Business College of Guangdong University of Foreign StudiesGuangzhouChina

The distance between two vertices u and v in a connected graph G is the number of edges lying in a shortest path(geodesic)between them.A vertex x of G performs the metric identification for a pair(u,v)of vertices in G if and only if the equality between the distances of u and v with x implies that u=v(That is,the distance between u and x is different from the distance between v and x).The minimum number of vertices performing the metric identification for every pair of vertices in G defines themetric dimension of *** this paper,we performthemetric identification of vertices in two types of polygonal cacti:chain polygonal cactus and star polygonal cactus.

关键词： Metric metric identification metric generator metric dimension cactus graph

来源：评论

学校读者我要写书评

暂无评论

A hybrid technique for selection and minimization of test cases in regression testing

引用

Recent Advances in computer science and Communications 2021年第2期14卷 477-488页

作者： Singh, Leena Singh, Shailendra N. Dawra, Sudhir Department of Computer Science and Engineering Amity University Noida India Department of Computer Application Tecnia Institute of Advanced Studies New Delhi India

Background: In today’s era, modifications in a software is a common requirement by customers. When changes are made to existing software, re-testing of all the test cases is required to ensure that the newly introduced changes do not have any unwanted effect on the behavior of the software. However, re-testing of all the test cases would not only be time consuming but also expensive. Therefore, there is a need for a technique that reduces the number of tests to be performed. Regression testing is one of the ways to reduce the number of test cases. Selection technique is one such method which seeks to identify the test cases that are relevant to some set of recent changes. Objective: It is evident that most of the studies have used different selection techniques and have focused only on one parameter for achieving reduced test suite size without compromising the performance of regression testing. However, to the best of our knowledge, no study has taken two or more parameters of cov-erage, and/or execution time in a single testing. This paper presents a hybrid technique that combines both regression test selection using slicing technique and minimization of test cases using modified firefly algorithm with combination of parameters coverage and execution time in a single testing. Methods: A hybrid technique has been described that combines both selection and minimization. Selection of test cases is based upon slicing technique while minimization is done using firefly algorithm. Hybrid technique selects and minimizes the test suite using information on statement coverage and execution time. Results: The proposed technique gives 43.33% much superior result as compared to the other hybrid approach in terms of significantly reduced number of test cases. It shows that the resultant test cases were effective enough to cover 100% of the statements, for all the programs. The proposed technique was also tested on four different programs namely Quadratic, Triangle, Next day, Co

关键词： Testing

来源：评论

学校读者我要写书评

暂无评论

Fault Secured JPEG-Codec Hardware Accelerator with Piracy Detective Control using Secure Fingerprint Template 36

Fault Secured JPEG-Codec Hardware Accelerator with Piracy De...

引用

36th IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems, DFT 2023

作者： Chaurasia, Rahul Reddy Asireddy, Abhinav Sengupta, Anirban Indian Institute of Technology Computer Science and Engineering Indore India Indian Institute of Technology Department of Computer Science and Engineering Indore India Indian Statistical Institute Advanced Computing and Microelectronics Unit Kolkata India

ISBN: (纸本)9798350315004

This paper presents a novel methodology to design fault secured JPEG-compression-decompression (codec) hardware accelerator with piracy detective control using secure fingerprint template of intellectual property (IP) vendor. In the proposed approach, firstly, the fault secured schedule for JPEG-codec design is generated from its behavioral description. Subsequently, in order to enable detective control against piracy, secure digital template corresponding to fingerprint biometric of IP vendor is generated and implanted into the design. In order to do so, firstly, fingerprint features are transformed based on IP vendor specified key-set. Subsequently, the generated secure fingerprint template in the form of encoded hardware security constraints is implanted into the design during behavioral/ high-level synthesis phase of integrated circuit (IC) design. The implanted hardware security constraints thereby ensure the seamless detection and isolation of fake/pirated design versions during piracy detection process, before their conjunction into system on chip (SoC) of electronic systems. The proposed approach achieves the following: i) fault secured hardware accelerator for JPEG-codec with integrated piracy detective control at negligible design cost overhead ii) higher resiliency against tampering attack and iii) lower probability of coincidence (indicating definitive proof of ownership for genuine IP vendor). © 2023 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Object Tracking in Intelligent Video Surveillance System Based on Artificial System 1

Object Tracking in Intelligent Video Surveillance System Bas...

引用

1st International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023

作者： Choubisa, Mukesh Kumar, Vijay Kumar, Mukesh Khanna, Samrat Institute of Advanced Research Department of Computer Science and Engineering Gujarat Gandhinagar India Ministry of Electronics & It Indian Computer Emergency Response Team Delhi India

ISBN: (纸本)9798350338027

Object moving tracking is one of the furthermost attractive and critical chores in computer science and computer vision research domain. Object moving tracking is underpinned for various higher-level automated applications in different research domains such as surveillance of video, motion capture and Augmented Reality (AR) in computer vision. Object tracking is the significant section of an intelligent video surveillance system (IVS) which can be further used for finding many other apprehensive or suspicious activities. Through the independent and exhaustive research of the current object motion and moving tracking technology, collective with hands- on application of IVS (intelligent video surveillance). In computer science many different algorithms available for object path tracking, object tracking and object motion detection, but mean shift algorithm (MSA) is the most popular and basic approach. We use mean shift algorithm (MSA) for our research work. The proposed work in this paper with following objectives, a) Video series frame production for tracking of a moving body, b) Design of experiments for object detection, c) Formulation and implementation of an algorithm to detect object *** algorithm was applied on an image frame of a recorded video. Based on multiple input images, we were able to detect the object and track its successive image frames. The realistic execution may want to obtain the object body tracking without losing any input frame and could magnificently coat bounding field. After completion of the mean shift algorithm (MSA) it would be able to produce an image sequence. The maneuver and precision of the algorithm was tested by successfully overlay function in the identified object and user defined object. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Real-Time Anomaly Detection in Docker Containers: A Continuous Learning Approach Using SF-SOINN

Real-Time Anomaly Detection in Docker Containers: A Continuo...

引用

2025 Joint National Conference on Cybersecurity, ITASEC and SERICS 2025

作者： Ejeh, Dennis Glenn Foresti, Gian Luca Miculan, Marino De Nardin, Axel CYSEC IMT School for Advanced Studies Lucca Italy Department of Mathematics Computer Science and Physics University of Udine Italy

As cyber threats are becoming more sophisticated than ever with the rapid expansion of internet-connected systems and increased use of containerized environments, we present Soft-Forgetting Self-Organizing Incremental Neural Network (SF-SOINN), a novel approach to unsupervised anomaly detection in containerized platforms. Whereas traditional Intrusion Detection Systems (IDS) utilize supervised learning that uses known attack signatures for training, SF-SOINN employs a continuous learning approach to adapt dynamically to new data patterns, thereby eliminating the need for labeled datasets. This capability enables effective real-time detection of zero-day threats in dynamic environments. SF-SOINN have demonstrated efficacy in identifying malicious attacks on the real-world NSL-KDD dataset, and we extended its application to containerized environments, using the KubAnomaly framework. Our benchmark results reveal that SF-SOINN outperforms traditional supervised models like Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and unsupervised KubAnomaly, particularly in scenarios involving complex attacks. The performance metric considered here focused on the optimization of False Positive Rate (FPR), while balancing other key performance metrics like accuracy, recall, and precision to achieve best results - and we anticipate this approach will lay a strong foundation for developing robust anomaly IDS in future. © 2025 Copyright for this paper by its authors.

关键词： Zero-day attack

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：